Daily Papers

As language models shift from single-shot answer generation toward multi-step reasoning that retrieves and consumes evidence mid-inference, evaluating the role of individual retrieved items becomes more important. Existing RAG evaluation typically targets final-answer quality, citation faithfulness, or answer-level attribution, but none of these directly targets the intervention-based, per-evidence-item utility view we study here. We introduce CUE-R, a lightweight intervention-based framework for measuring per-evidence-item operational utility in single-shot RAG using shallow observable retrieval-use traces. CUE-R perturbs individual evidence items via REMOVE, REPLACE, and DUPLICATE operators, then measures changes along three utility axes (correctness, proxy-based grounding faithfulness, and confidence error) plus a trace-divergence signal. We also outline an operational evidence-role taxonomy for interpreting intervention outcomes. Experiments on HotpotQA and 2WikiMultihopQA with Qwen-3 8B and GPT-5.2 reveal a consistent pattern: REMOVE and REPLACE substantially harm correctness and grounding while producing large trace shifts, whereas DUPLICATE is often answer-redundant yet not fully behaviorally neutral. A zero-retrieval control confirms that these effects arise from degradation of meaningful retrieval. A two-support ablation further shows that multi-hop evidence items can interact non-additively: removing both supports harms performance far more than either single removal. Our results suggest that answer-only evaluation misses important evidence effects and that intervention-based utility analysis is a practical complement for RAG evaluation.

Vision-Language Models (VLMs) have advanced across multimodal benchmarks but still show clear gaps in ordinal number understanding, i.e., the ability to track relative positions and generalize to large indices. We present OrdinalBench, a diagnostic benchmark that standardizes ordinal number understanding as an evaluation task for VLMs. The core task is N-th object identification, defined by a starting reference and traversal rule. Task difficulty is controlled along three axes: (i) ordinal magnitude, from small numbers to extreme cases up to 300; (ii) arrangement complexity, from single loops to maze-like paths; and (iii) object count. The benchmark provides 39,000 question-answer pairs, each annotated with a ground-truth reasoning trajectory and balanced across difficulty levels for controlled large-scale testing. Beyond answer-only evaluation, our framework requires models to generate structured stepwise traces of the counting process and provides an open evaluation toolkit that measures both final accuracy and step-level path consistency. Zero-shot evaluations of GPT-5, Gemini 2.5 Flash Lite, Qwen2.5-VL, InternVL3.5, and Molmo reveal sharp degradation under large-ordinal and complex-path conditions, highlighting weak generalization despite strong scores on standard multimodal tasks. By framing ordinal number understanding as a core target, OrdinalBench provides a reproducible benchmark and diagnostic framework for developing VLMs with stronger sequential reasoning. All data and code are available at https://ordinalbench.github.io/

Large language models (LLMs) have demonstrated exceptional performance in various natural language processing tasks, yet their efficacy in more challenging and domain-specific tasks remains largely unexplored. This paper presents FinEval, a benchmark specifically designed for the financial domain knowledge in the LLMs. FinEval is a collection of high-quality multiple-choice questions covering Finance, Economy, Accounting, and Certificate. It includes 4,661 questions spanning 34 different academic subjects. To ensure a comprehensive model performance evaluation, FinEval employs a range of prompt types, including zero-shot and few-shot prompts, as well as answer-only and chain-of-thought prompts. Evaluating state-of-the-art Chinese and English LLMs on FinEval, the results show that only GPT-4 achieved an accuracy close to 70% in different prompt settings, indicating significant growth potential for LLMs in the financial domain knowledge. Our work offers a more comprehensive financial knowledge evaluation benchmark, utilizing data of mock exams and covering a wide range of evaluated LLMs.

We present Korean SimpleQA (KoSimpleQA), a benchmark for evaluating factuality in large language models (LLMs) with a focus on Korean cultural knowledge. KoSimpleQA is designed to be challenging yet easy to grade, consisting of 1,000 short, fact-seeking questions with unambiguous answers. We conduct a comprehensive evaluation across a diverse set of open-source LLMs of varying sizes that support Korean, and find that even the strongest model generates correct answer only 33.7% of the time, underscoring the challenging nature of KoSimpleQA. Notably, performance rankings on KoSimpleQA differ substantially from those on the English SimpleQA, highlighting the unique value of our dataset. Furthermore, our analysis of reasoning LLMs shows that engaging reasoning capabilities in the factual QA task can both help models better elicit their latent knowledge and improve their ability to abstain when uncertain. KoSimpleQA can be found at https://anonymous.4open.science/r/KoSimpleQA-62EB.

Multi-step spatial reasoning entails understanding and reasoning about spatial relationships across multiple sequential steps, which is crucial for tackling complex real-world applications, such as robotic manipulation, autonomous navigation, and automated assembly. To assess how well current Multimodal Large Language Models (MLLMs) have acquired this fundamental capability, we introduce LEGO-Puzzles, a scalable benchmark designed to evaluate both spatial understanding and sequential reasoning in MLLMs through LEGO-based tasks. LEGO-Puzzles consists of 1,100 carefully curated visual question-answering (VQA) samples spanning 11 distinct tasks, ranging from basic spatial understanding to complex multi-step reasoning. Based on LEGO-Puzzles, we conduct a comprehensive evaluation of state-of-the-art MLLMs and uncover significant limitations in their spatial reasoning capabilities: even the most powerful MLLMs can answer only about half of the test cases, whereas human participants achieve over 90\% accuracy. In addition to VQA tasks, we evaluate MLLMs' abilities to generate LEGO images following assembly illustrations. Our experiments show that only Gemini-2.0-Flash and GPT-4o exhibit a limited ability to follow these instructions, while other MLLMs either replicate the input image or generate completely irrelevant outputs. Overall, LEGO-Puzzles exposes critical deficiencies in existing MLLMs' spatial understanding and sequential reasoning capabilities, and underscores the need for further advancements in multimodal spatial reasoning.

While Small Language Models (SLMs) have demonstrated promising performance on an increasingly wide array of commonsense reasoning benchmarks, current evaluation practices rely almost exclusively on the accuracy of their final answers, neglecting the validity of the reasoning processes that lead to those answers. To address this issue, we introduce ReTraceQA, a novel benchmark that introduces process-level evaluation for commonsense reasoning tasks. Our expert-annotated dataset reveals that in a substantial portion of instances (14-24%), SLMs provide correct final answers despite flawed reasoning processes, suggesting that the capabilities of SLMs are often overestimated by evaluation metrics that focus only on comparing the final answer with the ground truth. Indeed, we show that when employing strong Large Language Models (LLMs) as automated judges for reasoning-aware evaluation rather than answer-only metrics, SLM performance drops significantly across all models and datasets, with scores decreasing by up to 25%.

We introduce PRISM-Bench, a benchmark of puzzle-based visual challenges designed to evaluate not only whether models can solve problems, but how their reasoning unfolds. Unlike prior evaluations that measure only final-answer accuracy, PRISM-Bench introduces a diagnostic task: given a visual puzzle and a step-by-step chain-of-thought (CoT) containing exactly one error, models must identify the first incorrect step. This setting enables fine-grained assessment of logical consistency, error detection, and visual reasoning. The puzzles in PRISM-Bench require multi-step symbolic, geometric, and analogical reasoning, resisting shortcuts based on superficial pattern matching. Evaluations across state-of-the-art MLLMs reveal a persistent gap between fluent generation and faithful reasoning: models that produce plausible CoTs often fail to locate simple logical faults. By disentangling answer generation from reasoning verification, PRISM-Bench offers a sharper lens on multimodal reasoning competence and underscores the need for diagnostic evaluation protocols in the development of trustworthy MLLMs.

Reasoning benchmarks have played a crucial role in the progress of language models. Yet rigorous evaluation remains a significant challenge as static question-answer pairs provide only a snapshot of performance, compressing complex behavior into a single accuracy metric. This limitation is especially true in complex, rule-bound domains such as law, where existing benchmarks are costly to build and ill suited for isolating specific failure modes. To address this, we introduce OpenExempt, a framework and benchmark for diagnostic evaluation of legal reasoning. The OpenExempt Framework uses expert-crafted symbolic representations of U.S. Bankruptcy Code statutes to dynamically generate a large space of natural language reasoning tasks and their machine-computable solutions on demand. This gives users fine-grained control over task complexity and scope, allowing individual reasoning skills to be probed in isolation. Using this system, we construct the OpenExempt Benchmark, a diagnostic benchmark for legal reasoning with 9,765 samples across nine evaluation suites designed to carefully probe model capabilities. Experiments on 13 diverse language models reveal sharp performance cliffs that emerge only under longer reasoning paths and in the presence of obfuscating statements. We release the framework and benchmark publicly to support research aimed at understanding and improving the next generation of reasoning systems.

Inequality proving, crucial across diverse scientific and mathematical fields, tests advanced reasoning skills such as discovering tight bounds and strategic theorem application. This makes it a distinct, demanding frontier for large language models (LLMs), offering insights beyond general mathematical problem-solving. Progress in this area is hampered by existing datasets that are often scarce, synthetic, or rigidly formal. We address this by proposing an informal yet verifiable task formulation, recasting inequality proving into two automatically checkable subtasks: bound estimation and relation prediction. Building on this, we release IneqMath, an expert-curated dataset of Olympiad-level inequalities, including a test set and training corpus enriched with step-wise solutions and theorem annotations. We also develop a novel LLM-as-judge evaluation framework, combining a final-answer judge with four step-wise judges designed to detect common reasoning flaws. A systematic evaluation of 29 leading LLMs on IneqMath reveals a surprising reality: even top models like o1 achieve less than 10% overall accuracy under step-wise scrutiny; this is a drop of up to 65.5% from their accuracy considering only final answer equivalence. This discrepancy exposes fragile deductive chains and a critical gap for current LLMs between merely finding an answer and constructing a rigorous proof. Scaling model size and increasing test-time computation yield limited gains in overall proof correctness. Instead, our findings highlight promising research directions such as theorem-guided reasoning and self-refinement. Code and data are available at https://ineqmath.github.io/.

Question answering (QA) can only make progress if we know if an answer is correct, but for many of the most challenging and interesting QA examples, current evaluation metrics to determine answer equivalence (AE) often do not align with human judgments, particularly more verbose, free-form answers from large language models (LLM). There are two challenges: a lack of data and that models are too big: LLM-based scorers can correlate better with human judges, but this task has only been tested on limited QA datasets, and even when available, update of the model is limited because LLMs are large and often expensive. We rectify both of these issues by providing clear and consistent guidelines for evaluating AE in machine QA adopted from professional human QA contests. We also introduce a combination of standard evaluation and a more efficient, robust, and lightweight discriminate AE classifier-based matching method (CFMatch, smaller than 1 MB), trained and validated to more accurately evaluate answer correctness in accordance with adopted expert AE rules that are more aligned with human judgments.

Question answering (QA) can only make progress if we know if an answer is correct, but for many of the most challenging and interesting QA examples, current answer correctness (AC) metrics do not align with human judgments, particularly verbose, free form answers from large language models (LLM). There are two challenges: a lack of data and that models are too big. LLM based scorers correlate better with humans, but this expensive task has only been tested on limited QA datasets. We rectify these issues by providing clear guidelines for evaluating machine QA adopted from human QA contests. We also introduce Precise ANswer correctness Determination and Adjudication (PANDA), a small, efficient, deterministic AC classifier (812 KB) that more accurately evaluates answer correctness.

Large Reasoning Models (LRMs) extend large language models with explicit, multi-step reasoning traces to enhance transparency and performance on complex tasks. However, these reasoning traces can be redundant or logically inconsistent, making them a new source of hallucination that is difficult to detect. Existing hallucination detection methods focus primarily on answer-level uncertainty and often fail to detect hallucinations or logical inconsistencies arising from the model's reasoning trace. This oversight is particularly problematic for LRMs, where the explicit thinking trace is not only an important support to the model's decision-making process but also a key source of potential hallucination. To this end, we propose RACE (Reasoning and Answer Consistency Evaluation), a novel framework specifically tailored for hallucination detection in LRMs. RACE operates by extracting essential reasoning steps and computing four diagnostic signals: inter-sample consistency of reasoning traces, entropy-based answer uncertainty, semantic alignment between reasoning and answers, and internal coherence of reasoning. This joint analysis enables fine-grained hallucination detection even when the final answer appears correct. Experiments across datasets and different LLMs demonstrate that RACE outperforms existing hallucination detection baselines, offering a robust and generalizable solution for evaluating LRMs. Our code is available at: https://github.com/bebr2/RACE.

Answer verification is crucial not only for evaluating large language models (LLMs) by matching their unstructured outputs against standard answers, but also serves as the reward model to guide LLM optimization. Most evaluation frameworks rely on regularized matching or employ general LLMs for answer verification, which demands extensive, repetitive customization for regex rules or evaluation prompts. Two fundamental limitations persist in current methodologies: 1) the absence of comprehensive benchmarks that systematically evaluate verification capabilities across different LLMs; and 2) the nascent stage of verifier development, where existing approaches lack both the robustness to handle complex edge cases and the generalizability across different domains. In this work, we develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward. It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types, including multi-subproblems, formulas, and sequence answers, while effectively identifying abnormal/invalid responses. We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier. We anticipate that CompassVerifier and VerifierBench will facilitate answer verification, evaluation protocols, and reinforcement learning research. Code and dataset are available at https://github.com/open-compass/CompassVerifier.

Achieving human-level performance on some of Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, it is necessary to provide both answer prediction and its explanation to further improve the MRC system's reliability, especially for real-life applications. In this paper, we propose a new benchmark called ExpMRC for evaluating the explainability of the MRC systems. ExpMRC contains four subsets, including SQuAD, CMRC 2018, RACE^+, and C^3 with additional annotations of the answer's evidence. The MRC systems are required to give not only the correct answer but also its explanation. We use state-of-the-art pre-trained language models to build baseline systems and adopt various unsupervised approaches to extract evidence without a human-annotated training set. The experimental results show that these models are still far from human performance, suggesting that the ExpMRC is challenging. Resources will be available through https://github.com/ymcui/expmrc

In light of recent breakthroughs in large language models (LLMs) that have revolutionized natural language processing (NLP), there is an urgent need for new benchmarks to keep pace with the fast development of LLMs. In this paper, we propose CFLUE, the Chinese Financial Language Understanding Evaluation benchmark, designed to assess the capability of LLMs across various dimensions. Specifically, CFLUE provides datasets tailored for both knowledge assessment and application assessment. In knowledge assessment, it consists of 38K+ multiple-choice questions with associated solution explanations. These questions serve dual purposes: answer prediction and question reasoning. In application assessment, CFLUE features 16K+ test instances across distinct groups of NLP tasks such as text classification, machine translation, relation extraction, reading comprehension, and text generation. Upon CFLUE, we conduct a thorough evaluation of representative LLMs. The results reveal that only GPT-4 and GPT-4-turbo achieve an accuracy exceeding 60\% in answer prediction for knowledge assessment, suggesting that there is still substantial room for improvement in current LLMs. In application assessment, although GPT-4 and GPT-4-turbo are the top two performers, their considerable advantage over lightweight LLMs is noticeably diminished. The datasets and scripts associated with CFLUE are openly accessible at https://github.com/aliyun/cflue.

Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While recent advances such as OpenAI o3 and GPT-4o demonstrate impressive perceptual and reasoning capabilities, our investigation reveals these models struggle profoundly with visual physical reasoning, failing to grasp basic physical laws, spatial interactions, and causal effects in complex scenes. More importantly, they often fail to follow coherent reasoning chains grounded in visual evidence, especially when multiple steps are needed to arrive at the correct answer. To rigorously evaluate this capability, we introduce MVPBench, a curated benchmark designed to rigorously evaluate visual physical reasoning through the lens of visual chain-of-thought (CoT). Each example features interleaved multi-image inputs and demands not only the correct final answer but also a coherent, step-by-step reasoning path grounded in evolving visual cues. This setup mirrors how humans reason through real-world physical processes over time. To ensure fine-grained evaluation, we introduce a graph-based CoT consistency metric that verifies whether the reasoning path of model adheres to valid physical logic. Additionally, we minimize shortcut exploitation from text priors, encouraging models to rely on visual understanding. Experimental results reveal a concerning trend: even cutting-edge MLLMs exhibit poor visual reasoning accuracy and weak image-text alignment in physical domains. Surprisingly, RL-based post-training alignment - commonly believed to improve visual reasoning performance - often harms spatial reasoning, suggesting a need to rethink current fine-tuning practices.

Multimodal Large Language Models (MLLMs) have achieved significant advancements in tasks like Visual Question Answering (VQA) by leveraging foundational Large Language Models (LLMs). However, their abilities in specific areas such as temporal understanding, which is crucial for comprehending real-world dynamics, remain underexplored. To address this, we propose a challenging evaluation benchmark named TemporalVQA, consisting of two parts: (1) Temporal Order Understanding and (2) Time-lapse Estimation. The first part requires MLLMs to determine the sequence of events by analyzing temporally consecutive video frames. The second part presents image pairs with varying time differences, framed as multiple-choice questions, asking MLLMs to estimate the time-lapse between images with options ranging from seconds to years. Our evaluations of advanced MLLMs, including models like GPT-4o and Gemini-1.5-Pro, reveal significant challenges: GPT-4o achieved only 43.8% average consistent accuracy in temporal order tasks and 70% in time-lapse estimation, with open-source models performing even less effectively. These findings underscore the limitations of current MLLMs in visual temporal understanding and reasoning, highlighting the need for further improvements in their temporal capabilities. Our dataset can be found at https://huggingface.co/datasets/fazliimam/temporal-vqa.

Multimodal/vision language models (VLMs) are increasingly being deployed in healthcare settings worldwide, necessitating robust benchmarks to ensure their safety, efficacy, and fairness. Multiple-choice question and answer (QA) datasets derived from national medical examinations have long served as valuable evaluation tools, but existing datasets are largely text-only and available in a limited subset of languages and countries. To address these challenges, we present WorldMedQA-V, an updated multilingual, multimodal benchmarking dataset designed to evaluate VLMs in healthcare. WorldMedQA-V includes 568 labeled multiple-choice QAs paired with 568 medical images from four countries (Brazil, Israel, Japan, and Spain), covering original languages and validated English translations by native clinicians, respectively. Baseline performance for common open- and closed-source models are provided in the local language and English translations, and with and without images provided to the model. The WorldMedQA-V benchmark aims to better match AI systems to the diverse healthcare environments in which they are deployed, fostering more equitable, effective, and representative applications.

LLMs trained on massive datasets may inadvertently acquire sensitive information such as personal details and potentially harmful content. This risk is further heightened in multimodal LLMs as they integrate information from multiple modalities (image and text). Adversaries can exploit this knowledge through multimodal prompts to extract sensitive details. Evaluating how effectively MLLMs can forget such information (targeted unlearning) necessitates the creation of high-quality, well-annotated image-text pairs. While prior work on unlearning has focused on text, multimodal unlearning remains underexplored. To address this gap, we first introduce a multimodal unlearning benchmark, UnLOK-VQA (Unlearning Outside Knowledge VQA), as well as an attack-and-defense framework to evaluate methods for deleting specific multimodal knowledge from MLLMs. We extend a visual question-answering dataset using an automated pipeline that generates varying-proximity samples for testing generalization and specificity, followed by manual filtering for maintaining high quality. We then evaluate six defense objectives against seven attacks (four whitebox, three blackbox), including a novel whitebox method leveraging interpretability of hidden states. Our results show multimodal attacks outperform text- or image-only ones, and that the most effective defense removes answer information from internal model states. Additionally, larger models exhibit greater post-editing robustness, suggesting that scale enhances safety. UnLOK-VQA provides a rigorous benchmark for advancing unlearning in MLLMs.

Large Language Models (LLMs) have demonstrated strong performance in question answering (QA) tasks. However, Multi-Answer Question Answering (MAQA), where a question may have several valid answers, remains challenging. Traditional QA settings often assume consistency across evidences, but MAQA can involve conflicting answers. Constructing datasets that reflect such conflicts is costly and labor-intensive, while existing benchmarks often rely on synthetic data, restrict the task to yes/no questions, or apply unverified automated annotation. To advance research in this area, we extend the conflict-aware MAQA setting to require models not only to identify all valid answers, but also to detect specific conflicting answer pairs, if any. To support this task, we introduce a novel cost-effective methodology for leveraging fact-checking datasets to construct NATCONFQA, a new benchmark for realistic, conflict-aware MAQA, enriched with detailed conflict labels, for all answer pairs. We evaluate eight high-end LLMs on NATCONFQA, revealing their fragility in handling various types of conflicts and the flawed strategies they employ to resolve them.

Retrieval-augmented generation (RAG) has emerged as a leading approach to reducing hallucinations in large language models (LLMs). Current RAG evaluation benchmarks primarily focus on what we call local RAG: retrieving relevant chunks from a small subset of documents to answer queries that require only localized understanding within specific text chunks. However, many real-world applications require a fundamentally different capability -- global RAG -- which involves aggregating and analyzing information across entire document collections to derive corpus-level insights (for example, "What are the top 10 most cited papers in 2023?"). In this paper, we introduce GlobalQA -- the first benchmark specifically designed to evaluate global RAG capabilities, covering four core task types: counting, extremum queries, sorting, and top-k extraction. Through systematic evaluation across different models and baselines, we find that existing RAG methods perform poorly on global tasks, with the strongest baseline achieving only 1.51 F1 score. To address these challenges, we propose GlobalRAG, a multi-tool collaborative framework that preserves structural coherence through chunk-level retrieval, incorporates LLM-driven intelligent filters to eliminate noisy documents, and integrates aggregation modules for precise symbolic computation. On the Qwen2.5-14B model, GlobalRAG achieves 6.63 F1 compared to the strongest baseline's 1.51 F1, validating the effectiveness of our method.

Large Multimodal Models (LMMs) are increasingly applied to scientific research, yet it remains unclear whether they can reliably understand and reason over the multimodal complexity of papers. A central challenge lies in detecting and resolving inconsistencies across text, figures, tables, and equations, issues that are often subtle, domain-specific, and ultimately undermine clarity, reproducibility, and trust. Existing benchmarks overlook this issue, either isolating single modalities or relying on synthetic errors that fail to capture real-world complexity. We introduce PRISMM-Bench (Peer-Review-sourced Inconsistency Set for Multimodal Models), the first benchmark grounded in real reviewer-flagged inconsistencies in scientific papers. Through a multi-stage pipeline of review mining, LLM-assisted filtering and human verification, we curate 262 inconsistencies from 242 papers. Based on this set, we design three tasks, namely inconsistency identification, remedy and pair matching, which assess a model's capacity to detect, correct, and reason over inconsistencies across different modalities. Furthermore, to address the notorious problem of choice-only shortcuts in multiple-choice evaluation, where models exploit answer patterns without truly understanding the question, we further introduce structured JSON-based answer representations that minimize linguistic biases by reducing reliance on superficial stylistic cues. We benchmark 21 leading LMMs, including large open-weight models (GLM-4.5V 106B, InternVL3 78B) and proprietary models (Gemini 2.5 Pro, GPT-5 with high reasoning). Results reveal strikingly low performance (26.1-54.2%), underscoring the challenge of multimodal scientific reasoning and motivating progress towards trustworthy scientific assistants.

We present AMO-Bench, an Advanced Mathematical reasoning benchmark with Olympiad level or even higher difficulty, comprising 50 human-crafted problems. Existing benchmarks have widely leveraged high school math competitions for evaluating mathematical reasoning capabilities of large language models (LLMs). However, many existing math competitions are becoming less effective for assessing top-tier LLMs due to performance saturation (e.g., AIME24/25). To address this, AMO-Bench introduces more rigorous challenges by ensuring all 50 problems are (1) cross-validated by experts to meet at least the International Mathematical Olympiad (IMO) difficulty standards, and (2) entirely original problems to prevent potential performance leakages from data memorization. Moreover, each problem in AMO-Bench requires only a final answer rather than a proof, enabling automatic and robust grading for evaluation. Experimental results across 26 LLMs on AMO-Bench show that even the best-performing model achieves only 52.4% accuracy on AMO-Bench, with most LLMs scoring below 40%. Beyond these poor performances, our further analysis reveals a promising scaling trend with increasing test-time compute on AMO-Bench. These results highlight the significant room for improving the mathematical reasoning in current LLMs. We release AMO-Bench to facilitate further research into advancing the reasoning abilities of language models. https://amo-bench.github.io/

Despite rapid advances in large language models (LLMs), achieving reliable performance on highly professional and structured examinations remains a significant challenge. The Japanese bar examination is a particularly demanding benchmark, requiring not only advanced legal reasoning but also strict adherence to complex answer formats that involve joint evaluation of multiple propositions. While recent studies have reported improvements by decomposing such questions into simpler true--false judgments, these approaches have not been systematically evaluated under the original exam format and scoring scheme, leaving open the question of whether they truly capture exam-level competence. In this paper, we present a self-verification model trained on a newly constructed dataset that faithfully replicates the authentic format and evaluation scale of the exam. Our model is able to exceed the official passing score when evaluated on the actual exam scale, marking the first demonstration, to our knowledge, of an LLM passing the Japanese bar examination without altering its original question structure or scoring rules. We further conduct extensive comparisons with alternative strategies, including multi-agent inference and decomposition-based supervision, and find that these methods fail to achieve comparable performance. Our results highlight the importance of format-faithful supervision and consistency verification, and suggest that carefully designed single-model approaches can outperform more complex systems in high-stakes professional reasoning tasks. Our dataset and codes are publicly available.

Despite recent advances in AI, the development of systems capable of executing complex, multi-step reasoning tasks involving multiple tools remains a significant challenge. Current benchmarks fall short in capturing the real-world complexity of tool-use reasoning, where verifying the correctness of not only the final answer but also the intermediate steps is important for evaluation, development, and identifying failures during inference time. To bridge this gap, we introduce ToolComp, a comprehensive benchmark designed to evaluate multi-step tool-use reasoning. ToolComp is developed through a collaboration between models and human annotators, featuring human-edited/verified prompts, final answers, and process supervision labels, allowing for the evaluation of both final outcomes and intermediate reasoning. Evaluation across six different model families demonstrates the challenging nature of our dataset, with the majority of models achieving less than 50% accuracy. Additionally, we generate synthetic training data to compare the performance of outcome-supervised reward models (ORMs) with process-supervised reward models (PRMs) to assess their ability to improve complex tool-use reasoning as evaluated by ToolComp. Our results show that PRMs generalize significantly better than ORMs, achieving a 19% and 11% improvement in rank@1 accuracy for ranking base and fine-tuned model trajectories, respectively. These findings highlight the critical role of process supervision in both the evaluation and training of AI models, paving the way for more robust and capable systems in complex, multi-step tool-use tasks.

The creation of high-quality datasets to improve Large Language Model (LLM) reasoning remains a significant challenge, as current methods often suffer from generating low-quality/incorrect answers and limited information richness from available data sources. To address this, we propose AgenticMath, a novel agentic pipeline for generating high-quality mathematical question-answer pairs to enhance the supervised fine-tuning of LLMs. Our method operates through four stages: (1) Seed Question Filter that selects questions with high information richness, complexity, and clarity; (2) an Agentic Question Rephrase step that employs a multi-agent system to generate diverse, logically consistent paraphrases; (3) an Answer Augment step where rewrite answers using chain-of-thought reasoning to enhance numerical and logical correctness, without reliance on human-provided labels; and (4) a final Question and Answer Evaluation that retains only the most superior pairs. Extensive experiments demonstrate that, fine-tuning 3B-8B parameter LLMs on AgenticMath generated datasets (comprising only 30-60K math samples) achieves competitive or superior performance on diverse in domain and out-of-domain mathematical reasoning benchmarks compared to baselines trained on much more data (e.g., 400K or 2.3M samples). Our work demonstrates that targeted, high-quality data generation is a more efficient path to improving mathematical reasoning in LLMs than large-scale, low-quality alternatives.

The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showcasing potential cognitive reasoning abilities in problem-solving and scientific discovery (i.e., AI4Science) once exclusive to human intellect. To comprehensively evaluate current models' performance in cognitive reasoning abilities, we introduce OlympicArena, which includes 11,163 bilingual problems across both text-only and interleaved text-image modalities. These challenges encompass a wide range of disciplines spanning seven fields and 62 international Olympic competitions, rigorously examined for data leakage. We argue that the challenges in Olympic competition problems are ideal for evaluating AI's cognitive reasoning due to their complexity and interdisciplinary nature, which are essential for tackling complex scientific challenges and facilitating discoveries. Beyond evaluating performance across various disciplines using answer-only criteria, we conduct detailed experiments and analyses from multiple perspectives. We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions. Our extensive evaluations reveal that even advanced models like GPT-4o only achieve a 39.97% overall accuracy, illustrating current AI limitations in complex reasoning and multimodal integration. Through the OlympicArena, we aim to advance AI towards superintelligence, equipping it to address more complex challenges in science and beyond. We also provide a comprehensive set of resources to support AI research, including a benchmark dataset, an open-source annotation platform, a detailed evaluation tool, and a leaderboard with automatic submission features.

Evaluating whether multimodal large language models truly understand long-form scientific papers remains challenging: answer-only metrics and synthetic "Needle-In-A-Haystack" tests often reward answer matching without requiring a causal, evidence-linked reasoning trace in the document. We propose the "Fish-in-the-Ocean" (FITO) paradigm, which requires models to construct explicit cross-modal evidence chains within native scientific documents. To operationalize FITO, we build SIN-Data, a scientific interleaved corpus that preserves the native interleaving of text and figures. On top of it, we construct SIN-Bench with four progressive tasks covering evidence discovery (SIN-Find), hypothesis verification (SIN-Verify), grounded QA (SIN-QA), and evidence-anchored synthesis (SIN-Summary). We further introduce "No Evidence, No Score", scoring predictions when grounded to verifiable anchors and diagnosing evidence quality via matching, relevance, and logic. Experiments on eight MLLMs show that grounding is the primary bottleneck: Gemini-3-pro achieves the best average overall score (0.573), while GPT-5 attains the highest SIN-QA answer accuracy (0.767) but underperforms on evidence-aligned overall scores, exposing a gap between correctness and traceable support.

Recent advances in large vision-language models have led to impressive performance in visual question answering and multimodal reasoning. However, it remains unclear whether these models genuinely perform grounded visual reasoning or rely on superficial patterns and dataset biases. In this work, we introduce MagiC, a comprehensive benchmark designed to evaluate grounded multimodal cognition, assessing not only answer accuracy but also the quality of step-by-step reasoning and its alignment with relevant visual evidence. Our benchmark includes approximately 5,500 weakly supervised QA examples generated from strong model outputs and 900 human-curated examples with fine-grained annotations, including answers, rationales, and bounding box groundings. We evaluate 15 vision-language models ranging from 7B to 70B parameters across four dimensions: final answer correctness, reasoning validity, grounding fidelity, and self-correction ability. MagiC further includes diagnostic settings to probe model robustness under adversarial visual cues and assess their capacity for introspective error correction. We introduce new metrics such as MagiScore and StepSense, and provide comprehensive analyses that reveal key limitations and opportunities in current approaches to grounded visual reasoning.

We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing ~0.25M images, ~0.76M questions, and ~10M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines and methods for VQA are provided and compared with human performance. Our VQA demo is available on CloudCV (http://cloudcv.org/vqa).

Logical reasoning consistently plays a fundamental and significant role in the domains of knowledge engineering and artificial intelligence. Recently, Large Language Models (LLMs) have emerged as a noteworthy innovation in natural language processing (NLP), exhibiting impressive achievements across various classic NLP tasks. However, the question of whether LLMs can effectively address the task of logical reasoning, which requires gradual cognitive inference similar to human intelligence, remains unanswered. To this end, we aim to bridge this gap and provide comprehensive evaluations in this paper. Firstly, to offer systematic evaluations, we select fifteen typical logical reasoning datasets and organize them into deductive, inductive, abductive and mixed-form reasoning settings. Considering the comprehensiveness of evaluations, we include three representative LLMs (i.e., text-davinci-003, ChatGPT and BARD) and evaluate them on all selected datasets under zero-shot, one-shot and three-shot settings. Secondly, different from previous evaluations relying only on simple metrics (e.g., accuracy), we propose fine-level evaluations from objective and subjective manners, covering both answers and explanations. Additionally, to uncover the logical flaws of LLMs, problematic cases will be attributed to five error types from two dimensions, i.e., evidence selection process and reasoning process. Thirdly, to avoid the influences of knowledge bias and purely focus on benchmarking the logical reasoning capability of LLMs, we propose a new dataset with neutral content. It contains 3,000 samples and covers deductive, inductive and abductive settings. Based on the in-depth evaluations, this paper finally forms a general evaluation scheme of logical reasoning capability from six dimensions. It reflects the pros and cons of LLMs and gives guiding directions for future works.

Mathematical reasoning in Large Language Models (LLMs) is often evaluated using benchmarks with limited numerical ranges, failing to reflect real-world problem-solving across diverse scales. Furthermore, most existing evaluation methods only compare model outputs to ground-truth answers, obscuring insights into reasoning processes. To address these limitations, we introduce GSM-Ranges, a dataset generator derived from GSM8K that systematically perturbs numerical values in math problems to assess model robustness across varying numerical scales. Additionally, we propose a novel grading methodology that distinguishes between logical and non-logical errors, offering a more precise evaluation of reasoning processes beyond computational accuracy. Our experiments with various models reveal a significant increase in logical error rates-up to 14 percentage points-as numerical complexity rises, demonstrating a general weakness in reasoning with out-of-distribution numerical values. Moreover, while models demonstrate high accuracy on standalone arithmetic tasks, their performance deteriorates substantially when computations are embedded within word problems. These findings provide a comprehensive evaluation of LLMs' mathematical reasoning capabilities and inform future research directions for improving numerical generalization in language models.

Retrieval-Augmented Generation (RAG) is a cornerstone of modern question answering (QA) systems, enabling grounded answers based on external knowledge. Although recent progress has been driven by open-domain datasets, enterprise QA systems need datasets that mirror the concrete, domain-specific issues users raise in day-to-day support scenarios. Critically, evaluating end-to-end RAG systems requires benchmarks comprising not only question--answer pairs but also the specific knowledge base (KB) snapshot from which answers were derived. To address this need, we introduce WixQA, a benchmark suite featuring QA datasets precisely grounded in the released KB corpus, enabling holistic evaluation of retrieval and generation components. WixQA includes three distinct QA datasets derived from Wix.com customer support interactions and grounded in a snapshot of the public Wix Help Center KB: (i) WixQA-ExpertWritten, 200 real user queries with expert-authored, multi-step answers; (ii) WixQA-Simulated, 200 expert-validated QA pairs distilled from user dialogues; and (iii) WixQA-Synthetic, 6,222 LLM-generated QA pairs, with one pair systematically derived from each article in the knowledge base. We release the KB snapshot alongside the datasets under MIT license and provide comprehensive baseline results, forming a unique benchmark for evaluating enterprise RAG systems in realistic enterprise environments.

With the rapid evolution of large language models (LLMs), new and hard-to-predict harmful capabilities are emerging. This requires developers to be able to identify risks through the evaluation of "dangerous capabilities" in order to responsibly deploy LLMs. In this work, we collect the first open-source dataset to evaluate safeguards in LLMs, and deploy safer open-source LLMs at a low cost. Our dataset is curated and filtered to consist only of instructions that responsible language models should not follow. We annotate and assess the responses of six popular LLMs to these instructions. Based on our annotation, we proceed to train several BERT-like classifiers, and find that these small classifiers can achieve results that are comparable with GPT-4 on automatic safety evaluation. Warning: this paper contains example data that may be offensive, harmful, or biased.

While Large Language Models (LLMs) can generate fluent and convincing responses, they are not necessarily correct. This is especially apparent in the popular decompose-then-verify factuality evaluation pipeline, where LLMs evaluate generations by decomposing the generations into individual, valid claims. Factuality evaluation is especially important for medical answers, since incorrect medical information could seriously harm the patient. However, existing factuality systems are a poor match for the medical domain, as they are typically only evaluated on objective, entity-centric, formulaic texts such as biographies and historical topics. This differs from condition-dependent, conversational, hypothetical, sentence-structure diverse, and subjective medical answers, which makes decomposition into valid facts challenging. We propose MedScore, a new pipeline to decompose medical answers into condition-aware valid facts and verify against in-domain corpora. Our method extracts up to three times more valid facts than existing methods, reducing hallucination and vague references, and retaining condition-dependency in facts. The resulting factuality score substantially varies by decomposition method, verification corpus, and used backbone LLM, highlighting the importance of customizing each step for reliable factuality evaluation by using our generalizable and modularized pipeline for domain adaptation.

Doctors and patients alike increasingly use Large Language Models (LLMs) to diagnose clinical cases. However, unlike domains such as math or coding, where correctness can be objectively defined by the final answer, medical diagnosis requires both the outcome and the reasoning process to be accurate. Currently, widely used medical benchmarks like MedQA and MMLU assess only accuracy in the final answer, overlooking the quality and faithfulness of the clinical reasoning process. To address this limitation, we introduce MedCaseReasoning, the first open-access dataset for evaluating LLMs on their ability to align with clinician-authored diagnostic reasoning. The dataset includes 14,489 diagnostic question-and-answer cases, each paired with detailed reasoning statements derived from open-access medical case reports. We evaluate state-of-the-art reasoning LLMs on MedCaseReasoning and find significant shortcomings in their diagnoses and reasoning: for instance, the top-performing open-source model, DeepSeek-R1, achieves only 48% 10-shot diagnostic accuracy and mentions only 64% of the clinician reasoning statements (recall). However, we demonstrate that fine-tuning LLMs on the reasoning traces derived from MedCaseReasoning significantly improves diagnostic accuracy and clinical reasoning recall by an average relative gain of 29% and 41%, respectively. The open-source dataset, code, and models are available at https://github.com/kevinwu23/Stanford-MedCaseReasoning.

Multimodal Large Language Models (MLLMs) have emerged to tackle the challenges of Visual Question Answering (VQA), sparking a new research focus on conducting objective evaluations of these models. Existing evaluation methods face limitations due to the significant human workload required to design Q&A pairs for visual images, which inherently restricts the scale and scope of evaluations. Although automated MLLM-as-judge approaches attempt to reduce the human workload through automatic evaluations, they often introduce biases. To address these problems, we propose an Unsupervised Peer review MLLM Evaluation framework. It utilizes only image data, allowing models to automatically generate questions and conduct peer review assessments of answers from other models, effectively alleviating the reliance on human workload. Additionally, we introduce the vision-language scoring system to mitigate the bias issues, which focuses on three aspects: (i) response correctness; (ii) visual understanding and reasoning; and (iii) image-text correlation. Experimental results demonstrate that UPME achieves a Pearson correlation of 0.944 with human evaluations on the MMstar dataset and 0.814 on the ScienceQA dataset, indicating that our framework closely aligns with human-designed benchmarks and inherent human preferences.

With the rapid advancement of Large Language Models (LLMs), long-context information understanding and processing have become a hot topic in academia and industry. However, benchmarks for evaluating the ability of LLMs to handle long-context information do not seem to have kept pace with the development of LLMs. Despite the emergence of various long-context evaluation benchmarks, the types of capability assessed are still limited, without new capability dimensions. In this paper, we introduce DetectiveQA, a narrative reasoning benchmark featured with an average context length of over 100K tokens. DetectiveQA focuses on evaluating the long-context reasoning ability of LLMs, which not only requires a full understanding of context but also requires extracting important evidences from the context and reasoning according to extracted evidences to answer the given questions. This is a new dimension of capability evaluation, which is more in line with the current intelligence level of LLMs. We use detective novels as data sources, which naturally have various reasoning elements. Finally, we manually annotated 600 questions in Chinese and then also provided an English edition of the context information and questions. We evaluate many long-context LLMs on DetectiveQA, including commercial and open-sourced models, and the results indicate that existing long-context LLMs still require significant advancements to effectively process true long-context dependency questions.

Audio-visual understanding is a rapidly evolving field that seeks to integrate and interpret information from both auditory and visual modalities. Despite recent advances in multi-modal learning, existing benchmarks often suffer from strong visual bias -- where answers can be inferred from visual data alone -- and provide only aggregate scores that conflate multiple sources of error. This makes it difficult to determine whether models struggle with visual understanding, audio interpretation, or audio-visual alignment. In this work, we introduce DAVE (Diagnostic Audio Visual Evaluation), a novel benchmark dataset designed to systematically evaluate audio-visual models across controlled challenges. DAVE alleviates existing limitations by (i) ensuring both modalities are necessary to answer correctly and (ii) decoupling evaluation into atomic subcategories. Our detailed analysis of state-of-the-art models reveals specific failure modes and provides targeted insights for improvement. By offering this standardized diagnostic framework, we aim to facilitate more robust development of audio-visual models. The dataset is released: https://github.com/gorjanradevski/dave

Following the success of Large Language Models (LLMs), Large Multimodal Models (LMMs), such as the Flamingo model and its subsequent competitors, have started to emerge as natural steps towards generalist agents. However, interacting with recent LMMs reveals major limitations that are hardly captured by the current evaluation benchmarks. Indeed, task performances (e.g., VQA accuracy) alone do not provide enough clues to understand their real capabilities, limitations, and to which extent such models are aligned to human expectations. To refine our understanding of those flaws, we deviate from the current evaluation paradigm, and (1) evaluate 10 recent open-source LMMs from 3B up to 80B parameter scale, on 5 different axes; hallucinations, abstention, compositionality, explainability and instruction following. Our evaluation on these axes reveals major flaws in LMMs. While the current go-to solution to align these models is based on training, such as instruction tuning or RLHF, we rather (2) explore the training-free in-context learning (ICL) as a solution, and study how it affects these limitations. Based on our ICL study, (3) we push ICL further and propose new multimodal ICL variants such as; Multitask-ICL, Chain-of-Hindsight-ICL, and Self-Correcting-ICL. Our findings are as follows. (1) Despite their success, LMMs have flaws that remain unsolved with scaling alone. (2) The effect of ICL on LMMs flaws is nuanced; despite its effectiveness for improved explainability, answer abstention, ICL only slightly improves instruction following, does not improve compositional abilities, and actually even amplifies hallucinations. (3) The proposed ICL variants are promising as post-hoc approaches to efficiently tackle some of those flaws. The code is available here: https://github.com/mshukor/EvALign-ICL.

Large Vision-Language Models (LVLMs) excel in multimodal reasoning and have shown impressive performance on various multimodal benchmarks. However, most of these benchmarks evaluate models primarily through multiple-choice or short-answer formats, which do not take the reasoning process into account. Although some benchmarks assess the reasoning process, their methods are often overly simplistic and only examine reasoning when answers are incorrect. This approach overlooks scenarios where flawed reasoning leads to correct answers. In addition, these benchmarks do not consider the impact of intermodal relationships on reasoning. To address this issue, we propose the Reasoning Process Tree Score (RPTS), a tree structure-based metric to assess reasoning processes. Specifically, we organize the reasoning steps into a reasoning tree and leverage its hierarchical information to assign weighted faithfulness scores to each reasoning step. By dynamically adjusting these weights, RPTS not only evaluates the overall correctness of the reasoning, but also pinpoints where the model fails in the reasoning. To validate RPTS in real-world multimodal scenarios, we construct a new benchmark, RPTS-Eval, comprising 374 images and 390 reasoning instances. Each instance includes reliable visual-textual clues that serve as leaf nodes of the reasoning tree. Furthermore, we define three types of intermodal relationships to investigate how intermodal interactions influence the reasoning process. We evaluated representative LVLMs (e.g., GPT4o, Llava-Next), uncovering their limitations in multimodal reasoning and highlighting the differences between open-source and closed-source commercial LVLMs. We believe that this benchmark will contribute to the advancement of research in the field of multimodal reasoning.

Logical reasoning is a critical component of Large Language Models (LLMs), and substantial research efforts in recent years have aimed to enhance their deductive reasoning capabilities. However, existing deductive reasoning benchmarks, which are crucial for evaluating and advancing LLMs, are inadequate due to their lack of task complexity, presence of prior knowledge as a confounder, and superficial error analysis. To address these deficiencies, we introduce JustLogic, a synthetically generated deductive reasoning benchmark designed for rigorous evaluation of LLMs. JustLogic is (i) highly complex, capable of generating a diverse range of linguistic patterns, vocabulary, and argument structures; (ii) prior knowledge independent, eliminating the advantage of models possessing prior knowledge and ensuring that only deductive reasoning is used to answer questions; and (iii) capable of in-depth error analysis on the heterogeneous effects of reasoning depth and argument form on model accuracy. Our experimental results on JustLogic reveal that most state-of-the-art (SOTA) LLMs perform significantly worse than the human average, demonstrating substantial room for model improvement. All code and data are available at https://github.com/michaelchen-lab/JustLogic

Video Question Answering (VideoQA) is a challenging task that entails complex multi-modal reasoning. In contrast to multiple-choice VideoQA which aims to predict the answer given several options, the goal of open-ended VideoQA is to answer questions without restricting candidate answers. However, the majority of previous VideoQA models formulate open-ended VideoQA as a classification task to classify the video-question pairs into a fixed answer set, i.e., closed-vocabulary, which contains only frequent answers (e.g., top-1000 answers). This leads the model to be biased toward only frequent answers and fail to generalize on out-of-vocabulary answers. We hence propose a new benchmark, Open-vocabulary Video Question Answering (OVQA), to measure the generalizability of VideoQA models by considering rare and unseen answers. In addition, in order to improve the model's generalization power, we introduce a novel GNN-based soft verbalizer that enhances the prediction on rare and unseen answers by aggregating the information from their similar words. For evaluation, we introduce new baselines by modifying the existing (closed-vocabulary) open-ended VideoQA models and improve their performances by further taking into account rare and unseen answers. Our ablation studies and qualitative analyses demonstrate that our GNN-based soft verbalizer further improves the model performance, especially on rare and unseen answers. We hope that our benchmark OVQA can serve as a guide for evaluating the generalizability of VideoQA models and inspire future research. Code is available at https://github.com/mlvlab/OVQA.

"Bigger the better" has been the predominant trend in recent Large Language Models (LLMs) development. However, LLMs do not suit well for scenarios that require on-device processing, energy efficiency, low memory footprint, and response efficiency. These requisites are crucial for privacy, security, and sustainable deployment. This paper explores the "less is more" paradigm by addressing the challenge of designing accurate yet efficient Small Language Models (SLMs) for resource constrained devices. Our primary contribution is the introduction of an accurate and fully transparent open-source 0.5 billion (0.5B) parameter SLM, named MobiLlama, catering to the specific needs of resource-constrained computing with an emphasis on enhanced performance with reduced resource demands. MobiLlama is a SLM design that initiates from a larger model and applies a careful parameter sharing scheme to reduce both the pre-training and the deployment cost. Our work strives to not only bridge the gap in open-source SLMs but also ensures full transparency, where complete training data pipeline, training code, model weights, and over 300 checkpoints along with evaluation codes is available at : https://github.com/mbzuai-oryx/MobiLlama.

We introduce MediX-R1, an open-ended Reinforcement Learning (RL) framework for medical multimodal large language models (MLLMs) that enables clinically grounded, free-form answers beyond multiple-choice formats. MediX-R1 fine-tunes a baseline vision-language backbone with Group Based RL and a composite reward tailored for medical reasoning: an LLM-based accuracy reward that judges semantic correctness with a strict YES/NO decision, a medical embedding-based semantic reward to capture paraphrases and terminology variants, and lightweight format and modality rewards that enforce interpretable reasoning and modality recognition. This multi-signal design provides stable, informative feedback for open-ended outputs where traditional verifiable or MCQ-only rewards fall short. To measure progress, we propose a unified evaluation framework for both text-only and image+text tasks that uses a Reference-based LLM-as-judge in place of brittle string-overlap metrics, capturing semantic correctness, reasoning, and contextual alignment. Despite using only sim51K instruction examples, MediX-R1 achieves excellent results across standard medical LLM (text-only) and VLM (image + text) benchmarks, outperforming strong open-source baselines and delivering particularly large gains on open-ended clinical tasks. Our results demonstrate that open-ended RL with comprehensive reward signals and LLM-based evaluation is a practical path toward reliable medical reasoning in multimodal models. Our trained models, curated datasets and source code are available at https://medix.cvmbzuai.com

This paper introduces LongBench v2, a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks. LongBench v2 consists of 503 challenging multiple-choice questions, with contexts ranging from 8k to 2M words, across six major task categories: single-document QA, multi-document QA, long in-context learning, long-dialogue history understanding, code repository understanding, and long structured data understanding. To ensure the breadth and the practicality, we collect data from nearly 100 highly educated individuals with diverse professional backgrounds. We employ both automated and manual review processes to maintain high quality and difficulty, resulting in human experts achieving only 53.7% accuracy under a 15-minute time constraint. Our evaluation reveals that the best-performing model, when directly answers the questions, achieves only 50.1% accuracy. In contrast, the o1-preview model, which includes longer reasoning, achieves 57.7%, surpassing the human baseline by 4%. These results highlight the importance of enhanced reasoning ability and scaling inference-time compute to tackle the long-context challenges in LongBench v2. The project is available at https://longbench2.github.io.

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find that simple CoT formats, where the model generates a reasoning step before the answer, not only fail to help, but can even harm the model's original performance. In contrast, structured multi-stage prompting based on scene graphs (SceneGraph CoT) significantly improves spatial reasoning accuracy. Furthermore, to improve spatial reasoning ability, we fine-tune models using Group Relative Policy Optimization (GRPO) on the SAT dataset and evaluate their performance on CVBench. Compared to supervised fine-tuning (SFT), GRPO achieves higher accuracy on Pass@1 evaluations and demonstrates superior robustness under out-of-distribution (OOD) conditions. In particular, we find that SFT overfits to surface-level linguistic patterns and may degrade performance when test-time phrasing changes (e.g., from "closer to" to "farther from"). GRPO, on the other hand, generalizes more reliably and maintains stable performance under such shifts. Our findings provide insights into how reinforcement learning and structured prompting improve the spatial reasoning capabilities and generalization behavior of modern VLMs. All code is open source at: https://github.com/Yvonne511/spatial-vlm-investigator

Question answering based on retrieval augmented generation (RAG-QA) is an important research topic in NLP and has a wide range of real-world applications. However, most existing datasets for this task are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization. To address these limitations, we create Long-form RobustQA (LFRQA), a new dataset comprising human-written long-form answers that integrate short extractive answers from multiple documents into a single, coherent narrative, covering 26K queries and large corpora across seven different domains. We further propose RAG-QA Arena by directly comparing model-generated answers against LFRQA's answers using LLMs as evaluators. We show via extensive experiments that RAG-QA Arena and human judgments on answer quality are highly correlated. Moreover, only 41.3% of the most competitive LLM's answers are preferred to LFRQA's answers, demonstrating RAG-QA Arena as a challenging evaluation platform for future research.

Graph-RAG systems achieve strong multi-hop question answering by indexing documents into knowledge graphs, but strong retrieval does not guarantee strong answers. Evaluating KET-RAG, a leading Graph-RAG system, on three multi-hop QA benchmarks (HotpotQA, MuSiQue, 2WikiMultiHopQA), we find that 77% to 91% of questions have the gold answer in the retrieved context, yet accuracy is only 35% to 78%, and 73% to 84% of errors are reasoning failures. We propose two augmentations: (i) SPARQL chain-of-thought prompting, which decomposes questions into triple-pattern queries aligned with the entity-relationship context, and (ii) graph-walk compression, which compresses the context by ~60% via knowledge-graph traversal with no LLM calls. SPARQL CoT improves accuracy by +2 to +14 pp; graph-walk compression adds +6 pp on average when paired with structured prompting on smaller models. Surprisingly, we show that, with question-type routing, a fully augmented budget open-weight Llama-8B model matches or exceeds the unaugmented Llama-70B baseline on all three benchmarks at ~12x lower cost. A replication on LightRAG confirms that our augmentations transfer across Graph-RAG systems.

Recent advancements in language models have led to significant improvements in mathematical reasoning across various benchmarks. However, most of these benchmarks rely on automatic evaluation methods that only compare final answers using heuristics, without verifying the underlying reasoning steps. This limitation results in false positive solutions, where models may produce correct final answers but with flawed deduction paths. In this paper, we systematically examine the prevalence of false positive solutions in mathematical problem solving for language models. We analyze the characteristics and extent of this issue across different open-source models, datasets of varying difficulty levels, and decoding strategies. Specifically, we explore how false positives influence the inference time scaling behavior of language models. Our experimental results reveal that: (1) false positive solutions persist across different models, datasets, and decoding methods, (2) sampling-based inference time scaling methods do not alleviate the problem, and (3) the pass@N evaluation metric is more susceptible to false positives, suggesting a significantly lower scaling ceiling than what automatic evaluations indicate. Additionally, we analyze specific instances of false positives and discuss potential limitations in self-improvement techniques and synthetic data generation under such conditions. Our data and code are publicly available at https://github.com/Wloner0809/False-Positives-in-Math.

We introduce FrontierScience, a benchmark evaluating expert-level scientific reasoning in frontier language models. Recent model progress has nearly saturated existing science benchmarks, which often rely on multiple-choice knowledge questions or already published information. FrontierScience addresses this gap through two complementary tracks: (1) Olympiad, consisting of international olympiad problems at the level of IPhO, IChO, and IBO, and (2) Research, consisting of PhD-level, open-ended problems representative of sub-tasks in scientific research. FrontierScience contains several hundred questions (including 160 in the open-sourced gold set) covering subfields across physics, chemistry, and biology, from quantum electrodynamics to synthetic organic chemistry. All Olympiad problems are originally produced by international Olympiad medalists and national team coaches to ensure standards of difficulty, originality, and factuality. All Research problems are research sub-tasks written and verified by PhD scientists (doctoral candidates, postdoctoral researchers, or professors). For Research, we introduce a granular rubric-based evaluation framework to assess model capabilities throughout the process of solving a research task, rather than judging only a standalone final answer.

Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Recently, reward models (RMs) have become increasingly pivotal in the reasoning process. Specifically, process RMs evaluate each reasoning step, outcome RMs focus on the assessment of reasoning results, and critique RMs perform error analysis on the entire reasoning process, followed by corrections. However, existing benchmarks for vision-language RMs (VLRMs) typically assess only a single aspect of their capabilities (e.g., distinguishing between two answers), thus limiting the all-round evaluation and restricting the development of RMs in the visual-language domain. To address this gap, we propose a comprehensive and challenging benchmark, dubbed as VLRMBench, encompassing 12,634 questions. VLRMBench is constructed based on three distinct types of datasets, covering mathematical reasoning, hallucination understanding, and multi-image understanding. We design 12 tasks across three major categories, focusing on evaluating VLRMs in the aspects of process understanding, outcome judgment, and critique generation. Extensive experiments are conducted on 21 open-source models and 5 advanced closed-source models, highlighting the challenges posed by VLRMBench. For instance, in the `Forecasting Future', a binary classification task, the advanced GPT-4o achieves only a 76.0% accuracy. Additionally, we perform comprehensive analytical studies, offering valuable insights for the future development of VLRMs. We anticipate that VLRMBench will serve as a pivotal benchmark in advancing VLRMs. Code and datasets will be available at https://github.com/JCruan519/VLRMBench.

We present SimpleQA, a benchmark that evaluates the ability of language models to answer short, fact-seeking questions. We prioritized two properties in designing this eval. First, SimpleQA is challenging, as it is adversarially collected against GPT-4 responses. Second, responses are easy to grade, because questions are created such that there exists only a single, indisputable answer. Each answer in SimpleQA is graded as either correct, incorrect, or not attempted. A model with ideal behavior would get as many questions correct as possible while not attempting the questions for which it is not confident it knows the correct answer. SimpleQA is a simple, targeted evaluation for whether models "know what they know," and our hope is that this benchmark will remain relevant for the next few generations of frontier models. SimpleQA can be found at https://github.com/openai/simple-evals.

Multiple choice benchmarks have long been the workhorse of language model evaluation because grading multiple choice is objective and easy to automate. However, we show multiple choice questions from popular benchmarks can often be answered without even seeing the question. These shortcuts arise from a fundamental limitation of discriminative evaluation not shared by evaluations of the model's free-form, generative answers. Until recently, there appeared to be no viable, scalable alternative to multiple choice--but, we show that this has changed. We consider generative evaluation via what we call answer matching: Give the candidate model the question without the options, have it generate a free-form response, then use a modern language model with the reference answer to determine if the response matches the reference. To compare the validity of different evaluation strategies, we annotate MMLU-Pro and GPQA-Diamond to obtain human grading data, and measure the agreement of each evaluation approach. We find answer matching using recent models--even small ones--achieves near-perfect agreement, in the range of inter-annotator agreement. In contrast, both multiple choice evaluation and using LLM-as-a-judge without reference answers aligns poorly with human grading. Improving evaluations via answer matching is not merely a conceptual concern: the rankings of several models change significantly when evaluating their free-form responses with answer matching. In light of these findings, we discuss how to move the evaluation ecosystem from multiple choice to answer matching.

LLMs cannot reliably recognize their parametric knowledge boundaries and often hallucinate answers to outside-of-boundary questions. In contrast, humans recognize their limitations and can either seek external help for such questions or abstain. In this paper, we introduce MASH (Modeling Abstention via Selective Help-seeking), a training framework that readily extracts abstentions from LLMs. Our key idea is that any external help-seeking by an LLM, i.e. search tool use, can serve as a proxy for abstention if the external help (search) is appropriately penalized while simultaneously rewarding answer accuracy. MASH operationalizes this idea using reinforcement learning with a pay-per-search reward. We run experiments on three knowledge-intensive QA datasets. Our results show that MASH substantially improves upon the selective help-seeking performance of prior efficient search approaches; on multi-hop datasets, MASH improves answer accuracy by 7.6%. Furthermore, MASH demonstrates strong off-the-shelf abstention -- it can distinguish between unanswerable/answerable questions and selectively generate responses for answerable questions -- showcasing behavior analogous to specialized abstention approaches. We emphasize that contrary to prior abstention methods, MASH does not require pre-determining knowledge boundaries to construct training data. Instead, MASH's abstentions are a by-product of training for the auxiliary selective help-seeking task. Overall, we show that MASH training effectively aligns search tool use with parametric knowledge, which can be successfully leveraged for making abstention decisions.

Recent progress in reasoning models suggests that generating plausible attempts for research-level mathematics may be within reach, but verification remains a bottleneck, consuming scarce expert time. We hypothesize that a meaningful solution should contain enough method-level information that, when applied to a neighborhood of related questions, it should yield better downstream performance than incorrect solutions. Building on this idea, we propose Consequence-Based Utility, an oracle-free evaluator that scores each candidate by testing its value as an in-context exemplar in solving related yet verifiable questions. Our approach is evaluated on an original set of research-level math problems, each paired with one expert-written solution and nine LLM-generated solutions. Notably, Consequence-Based Utility consistently outperforms reward models, generative reward models, and LLM judges on ranking quality. Specifically, for GPT-OSS-120B, it improves Acc@1 from 67.2 to 76.3 and AUC from 71.4 to 79.6, with similarly large AUC gains on GPT-OSS-20B (69.0 to 79.2). Furthermore, compared to LLM-Judges, it also exhibits a larger solver-evaluator gap, maintaining a stronger correct-wrong separation even on instances where the underlying solver often fails to solve.

Multiple-choice question answering (MCQA) is often used to evaluate large language models (LLMs). To see if MCQA assesses LLMs as intended, we probe if LLMs can perform MCQA with choices-only prompts, where models must select the correct answer only from the choices. In three MCQA datasets and four LLMs, this prompt bests a majority baseline in 11/12 cases, with up to 0.33 accuracy gain. To help explain this behavior, we conduct an in-depth, black-box analysis on memorization, choice dynamics, and question inference. Our key findings are threefold. First, we find no evidence that the choices-only accuracy stems from memorization alone. Second, priors over individual choices do not fully explain choices-only accuracy, hinting that LLMs use the group dynamics of choices. Third, LLMs have some ability to infer a relevant question from choices, and surprisingly can sometimes even match the original question. We hope to motivate the use of stronger baselines in MCQA benchmarks, the design of robust MCQA datasets, and further efforts to explain LLM decision-making.

Nowadays, the quality of responses generated by different modern large language models (LLMs) are hard to evaluate and compare automatically. Recent studies suggest and predominantly use LLMs as a reference-free metric for open-ended question answering. More specifically, they use the recognized "strongest" LLM as the evaluator, which conducts pairwise comparisons of candidate models' answers and provides a ranking score. However, this intuitive method has multiple problems, such as bringing in self-enhancement (favoring its own answers) and positional bias. We draw insights and lessons from the educational domain (Cho and MacArthur, 2011; Walsh, 2014) to improve LLM-based evaluations. Specifically, we propose the (1) peer rank (PR) algorithm that takes into account each peer LLM's pairwise preferences of all answer pairs, and outputs a final ranking of models; and (2) peer discussion (PD), where we prompt two LLMs to discuss and try to reach a mutual agreement on preferences of two answers. We conduct experiments on two benchmark datasets. We find that our approaches achieve higher accuracy and align better with human judgments, respectively. Interestingly, PR can induce a relatively accurate self-ranking of models under the anonymous setting, where each model's name is unrevealed. Our work provides space to explore evaluating models that are hard to compare for humans.

One of the most widely used methods to evaluate LLMs are Multiple Choice Question (MCQ) tests. MCQ benchmarks enable the testing of LLM knowledge on almost any topic at scale as the results can be processed automatically. To help the LLM answer, a few examples called few shots can be included in the prompt. Moreover, the LLM can be asked to answer the question directly with the selected option or to first provide the reasoning and then the selected answer, which is known as chain of thought. In addition to checking whether the selected answer is correct, the evaluation can look at the LLM-estimated probability of its response as an indication of the confidence of the LLM in the response. In this paper, we study how the LLM confidence in its answer depends on whether the model has been asked to answer directly or to provide the reasoning before answering. The results of the evaluation of questions on a wide range of topics in seven different models show that LLMs are more confident in their answers when they provide reasoning before the answer. This occurs regardless of whether the selected answer is correct. Our hypothesis is that this behavior is due to the reasoning that modifies the probability of the selected answer, as the LLM predicts the answer based on the input question and the reasoning that supports the selection made. Therefore, LLM estimated probabilities seem to have intrinsic limitations that should be understood in order to use them in evaluation procedures. Interestingly, the same behavior has been observed in humans, for whom explaining an answer increases confidence in its correctness.

RAG (Retrieval-Augmented Generation) systems and web agents are increasingly evaluated on multi-hop deep search tasks, yet current practice suffers from two major limitations. First, most benchmarks leak the reasoning path in the question text, allowing models to follow surface cues rather than discover reasoning chains autonomously. Second, evaluation is typically reduced to a single pass rate, which collapses diverse behaviours into one score and obscures whether failures stem from inadequate search, poor knowledge use, or inappropriate refusal. To address these issues, we present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox that ensures full traceability of model actions, and a holistic evaluation framework that separates search sufficiency, knowledge utilisation, and refusal behaviour. Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures: models struggle with knowledge utilisation despite having sufficient evidence and demonstrate near-absent appropriate refusal when evidence is lacking. These patterns expose a fundamental gap: today's systems excel at executing given reasoning paths but fail when required to discover them. We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies, incorporating verification loops and systematic evidence tracking that improve both search and synthesis capabilities. This baseline demonstrates that WebDetective's diagnostic framework can guide concrete architectural improvements, establishing our benchmark as a critical tool for developing genuinely autonomous reasoning systems rather than pattern-following agents.

Given questions regarding some prototypical situation such as Name something that people usually do before they leave the house for work? a human can easily answer them via acquired experiences. There can be multiple right answers for such questions, with some more common for a situation than others. This paper introduces a new question answering dataset for training and evaluating common sense reasoning capabilities of artificial intelligence systems in such prototypical situations. The training set is gathered from an existing set of questions played in a long-running international game show FAMILY- FEUD. The hidden evaluation set is created by gathering answers for each question from 100 crowd-workers. We also propose a generative evaluation task where a model has to output a ranked list of answers, ideally covering all prototypical answers for a question. After presenting multiple competitive baseline models, we find that human performance still exceeds model scores on all evaluation metrics with a meaningful gap, supporting the challenging nature of the task.

Automatic evaluation with large language models, commonly known as LLM-as-a-judge, is now standard across reasoning and alignment tasks. Despite evaluating many samples in deployment, these evaluators typically (i) treat each case independently, missing the opportunity to accumulate experience, and (ii) rely on a single fixed prompt for all cases, neglecting the need for sample-specific evaluation criteria. We introduce Learning While Evaluating (LWE), a framework that allows evaluators to improve sequentially at inference time without requiring training or validation sets. LWE maintains an evolving meta-prompt that (i) produces sample-specific evaluation instructions and (ii) refines itself through self-generated feedback. Furthermore, we propose Selective LWE, which updates the meta-prompt only on self-inconsistent cases, focusing computation where it matters most. This selective approach retains the benefits of sequential learning while being far more cost-effective. Across two pairwise comparison benchmarks, Selective LWE outperforms strong baselines, empirically demonstrating that evaluators can improve during sequential testing with a simple selective update, learning most from the cases they struggle with.

The recent emergence of Large Vision-Language Models(VLMs) has resulted in a variety of different benchmarks for evaluating such models. Despite this, we observe that most existing evaluation methods suffer from the fact that they either require the model to choose from pre-determined responses, sacrificing open-endedness, or evaluate responses using a judge model, resulting in subjective and unreliable evaluation. In addition, we observe a lack of benchmarks for VLMs in the Korean language, which are necessary as a separate metric from more common English language benchmarks, as the performance of generative language models can differ significantly based on the language being used. Therefore, we present KOFFVQA, a general-purpose free-form visual question answering benchmark in the Korean language for the evaluation of VLMs. Our benchmark consists of 275 carefully crafted questions each paired with an image and grading criteria covering 10 different aspects of VLM performance. The grading criteria eliminate the problem of unreliability by allowing the judge model to grade each response based on a pre-determined set of rules. By defining the evaluation criteria in an objective manner, even a small open-source model can be used to evaluate models on our benchmark reliably. In addition to evaluating a large number of existing VLMs on our benchmark, we also experimentally verify that our method of using pre-existing grading criteria for evaluation is much more reliable than existing methods. Our evaluation code is available at https://github.com/maum-ai/KOFFVQA

Medical reasoning models (MRMs) achieve superior performance on medical benchmarks compared to medical LLMs; however, high accuracy alone is insufficient for practical deployment. One of such requirements for real-world application is robustness to varying output constraints. Specifically, posing the same medical question while requesting different answer formats should not affect the underlying correctness of the response. We investigate this phenomenon in this paper, focusing on MRMs. To quantify this behavior, we propose the metric answer-format robustness: the ability to reliably generate correct outputs across varying specified formats. We examine three representative formats: multiple-choice, open-ended question-answering, and ranked lists. Across 15 proprietary and open-weight models, we observe substantial variation in format robustness (35-100%). Furthermore, we conduct controlled fine-tuning experiments on a shared backbone with matched training data to isolate the effects of the fine-tuning paradigm. We find that supervised fine-tuning yields more stable behavior across formats, whereas reinforcement fine-tuning often exhibits higher cross-format brittleness, with the degree of instability strongly dependent on reward design. Overall, answer-format robustness in MRMs is trainable yet brittle and requires careful evaluation for practical medical use.

8 years after the visual question answering (VQA) task was proposed, accuracy remains the primary metric for automatic evaluation. VQA Accuracy has been effective so far in the IID evaluation setting. However, our community is undergoing a shift towards open-ended generative models and OOD evaluation. In this new paradigm, the existing VQA Accuracy metric is overly stringent and underestimates the performance of VQA systems. Thus, there is a need to develop more robust automatic VQA metrics that serve as a proxy for human judgment. In this work, we propose to leverage the in-context learning capabilities of instruction-tuned large language models (LLMs) to build a better VQA metric. We formulate VQA evaluation as an answer-rating task where the LLM is instructed to score the accuracy of a candidate answer given a set of reference answers. We demonstrate the proposed metric better correlates with human judgment compared to existing metrics across several VQA models and benchmarks. We hope wide adoption of our metric will contribute to better estimating the research progress on the VQA task. We plan to release the evaluation code and collected human judgments.

Large Language Model (LLM)-based applications are graduating from research prototypes to products serving millions of users, influencing how people write and consume information. A prominent example is the appearance of Answer Engines: LLM-based generative search engines supplanting traditional search engines. Answer engines not only retrieve relevant sources to a user query but synthesize answer summaries that cite the sources. To understand these systems' limitations, we first conducted a study with 21 participants, evaluating interactions with answer vs. traditional search engines and identifying 16 answer engine limitations. From these insights, we propose 16 answer engine design recommendations, linked to 8 metrics. An automated evaluation implementing our metrics on three popular engines (You.com, Perplexity.ai, BingChat) quantifies common limitations (e.g., frequent hallucination, inaccurate citation) and unique features (e.g., variation in answer confidence), with results mirroring user study insights. We release our Answer Engine Evaluation benchmark (AEE) to facilitate transparent evaluation of LLM-based applications.

Multiple choice question answering (MCQA) is popular for LLM evaluation due to its simplicity and human-like testing, but we argue for its reform. We first reveal flaws in MCQA's format, as it struggles to: 1) test generation/subjectivity; 2) match LLM use cases; and 3) fully test knowledge. We instead advocate for generative formats based on human testing-where LLMs construct and explain answers-better capturing user needs and knowledge while remaining easy to score. We then show even when MCQA is a useful format, its datasets suffer from: leakage; unanswerability; shortcuts; and saturation. In each issue, we give fixes from education, like rubrics to guide MCQ writing; scoring methods to bridle guessing; and Item Response Theory to build harder MCQs. Lastly, we discuss LLM errors in MCQA-robustness, biases, and unfaithful explanations-showing how our prior solutions better measure or address these issues. While we do not need to desert MCQA, we encourage more efforts in refining the task based on educational testing, advancing evaluations.

Given a question, a language model (LM) implicitly encodes a distribution over possible answers. In practice, post-training procedures for LMs often collapse this distribution onto a single dominant mode. While this is generally not a problem for benchmark-style evaluations that assume one correct answer, many real-world tasks inherently involve multiple valid answers or irreducible uncertainty. Examples include medical diagnosis, ambiguous question answering, and settings with incomplete information. In these cases, we would like LMs to generate multiple plausible hypotheses, ideally with confidence estimates for each one, and without computationally intensive repeated sampling to generate non-modal answers. This paper describes a multi-answer reinforcement learning approach for training LMs to perform distributional reasoning over multiple answers during inference. We modify the RL objective to enable models to explicitly generate multiple candidate answers in a single forward pass, internalizing aspects of inference-time search into the model's generative process. Across question-answering, medical diagnostic, and coding benchmarks, we observe improved diversity, coverage, and set-level calibration scores compared to single answer trained baselines. Models trained with our approach require fewer tokens to generate multiple answers than competing approaches. On coding tasks, they are also substantially more accurate. These results position multi-answer RL as a principled and compute-efficient alternative to inference-time scaling procedures such as best-of-k. Code and more information can be found at https://multi-answer-rl.github.io/.

Most existing video understanding benchmarks for multimodal large language models (MLLMs) focus only on short videos. The limited number of benchmarks for long video understanding often rely solely on multiple-choice questions (MCQs). However, because of the inherent limitation of MCQ-based evaluation and the increasing reasoning ability of MLLMs, models can give the current answer purely by combining short video understanding with elimination, without genuinely understanding the video content. To address this gap, we introduce CG-Bench, a novel benchmark designed for clue-grounded question answering in long videos. CG-Bench emphasizes the model's ability to retrieve relevant clues for questions, enhancing evaluation credibility. It features 1,219 manually curated videos categorized by a granular system with 14 primary categories, 171 secondary categories, and 638 tertiary categories, making it the largest benchmark for long video analysis. The benchmark includes 12,129 QA pairs in three major question types: perception, reasoning, and hallucination. Compensating the drawbacks of pure MCQ-based evaluation, we design two novel clue-based evaluation methods: clue-grounded white box and black box evaluations, to assess whether the model generates answers based on the correct understanding of the video. We evaluate multiple closed-source and open-source MLLMs on CG-Bench. Results indicate that current models significantly underperform in understanding long videos compared to short ones, and a significant gap exists between open-source and commercial models. We hope CG-Bench can advance the development of more trustworthy and capable MLLMs for long video understanding. All annotations and video data are released at https://cg-bench.github.io/leaderboard/.

Question answering (QA) is a critical task for speech-based retrieval from knowledge sources, by sifting only the answers without requiring to read supporting documents. Specifically, open-domain QA aims to answer user questions on unrestricted knowledge sources. Ideally, adding a source should not decrease the accuracy, but we find this property (denoted as "monotonicity") does not hold for current state-of-the-art methods. We identify the cause, and based on that we propose Judge-Specialist framework. Our framework consists of (1) specialist retrievers/readers to cover individual sources, and (2) judge, a dedicated language model to select the final answer. Our experiments show that our framework not only ensures monotonicity, but also outperforms state-of-the-art multi-source QA methods on Natural Questions. Additionally, we show that our models robustly preserve the monotonicity against noise from speech recognition. We publicly release our code and setting.

While small language models (SLMs) have shown promise on various reasoning tasks, their ability to judge the correctness of answers remains unclear compared to large language models (LLMs). Prior work on LLM-as-a-judge frameworks typically relies on comparing candidate answers against ground-truth labels or other candidate answers using predefined metrics like entailment. However, this approach is inherently indirect and difficult to fully automate, offering limited support for fine-grained and scalable evaluation of reasoning outputs. In this work, we propose JudgeBoard, a novel evaluation pipeline that directly queries models to assess the correctness of candidate answers without requiring extra answer comparisons. We focus on two core reasoning domains: mathematical reasoning and science/commonsense reasoning, and construct task-specific evaluation leaderboards using both accuracy-based ranking and an Elo-based rating system across five benchmark datasets, enabling consistent model comparison as judges rather than comparators. To improve judgment performance in lightweight models, we propose MAJ (Multi-Agent Judging), a novel multi-agent evaluation framework that leverages multiple interacting SLMs with distinct reasoning profiles to approximate LLM-level judgment accuracy through collaborative deliberation. Experimental results reveal a significant performance gap between SLMs and LLMs in isolated judging tasks. However, our MAJ framework substantially improves the reliability and consistency of SLMs. On the MATH dataset, MAJ using smaller-sized models as backbones performs comparatively well or even better than their larger-sized counterparts. Our findings highlight that multi-agent SLM systems can potentially match or exceed LLM performance in judgment tasks, with implications for scalable and efficient assessment.

While Large Language Models (LLMs) have demonstrated proficiency in handling complex queries, much of the past work has depended on extensively annotated datasets by human experts. However, this reliance on fully-supervised annotations poses scalability challenges, particularly as models and data requirements grow. To mitigate this, we explore the potential of enhancing LLMs' reasoning abilities with minimal human supervision. In this work, we introduce self-reinforcement, which begins with Supervised Fine-Tuning (SFT) of the model using a small collection of annotated questions. Then it iteratively improves LLMs by learning from the differences in responses from the SFT and unfinetuned models on unlabeled questions. Our approach provides an efficient approach without relying heavily on extensive human-annotated explanations. However, current reasoning benchmarks typically only include golden-reference answers or rationales. Therefore, we present PuzzleBen, a weakly supervised benchmark that comprises 25,147 complex questions, answers, and human-generated rationales across various domains, such as brainteasers, puzzles, riddles, parajumbles, and critical reasoning tasks. A unique aspect of our dataset is the inclusion of 10,000 unannotated questions, enabling us to explore utilizing fewer supersized data to boost LLMs' inference capabilities. Our experiments underscore the significance of PuzzleBen, as well as the effectiveness of our methodology as a promising direction in future endeavors. Our dataset and code will be published soon on Anonymity Link.

Recent large language models often answer factual questions correctly. But users can't trust any given claim a model makes without fact-checking, because language models can hallucinate convincing nonsense. In this work we use reinforcement learning from human preferences (RLHP) to train "open-book" QA models that generate answers whilst also citing specific evidence for their claims, which aids in the appraisal of correctness. Supporting evidence is drawn from multiple documents found via a search engine, or from a single user-provided document. Our 280 billion parameter model, GopherCite, is able to produce answers with high quality supporting evidence and abstain from answering when unsure. We measure the performance of GopherCite by conducting human evaluation of answers to questions in a subset of the NaturalQuestions and ELI5 datasets. The model's response is found to be high-quality 80\% of the time on this Natural Questions subset, and 67\% of the time on the ELI5 subset. Abstaining from the third of questions for which it is most unsure improves performance to 90\% and 80\% respectively, approaching human baselines. However, analysis on the adversarial TruthfulQA dataset shows why citation is only one part of an overall strategy for safety and trustworthiness: not all claims supported by evidence are true.

When evaluating large language models (LLMs) with multiple-choice question answering (MCQA), it is common to end the prompt with the string "Answer:" to facilitate automated answer extraction via next-token probabilities. However, there is no consensus on how to tokenize the space following the colon, often overlooked as a trivial choice. In this paper, we uncover accuracy differences of up to 11% due to this (seemingly irrelevant) tokenization variation as well as reshuffled model rankings, raising concerns about the reliability of LLM comparisons in prior work. Surprisingly, we are able to recommend one specific strategy -- tokenizing the space together with the answer letter -- as we observe consistent and statistically significant performance improvements. Additionally, it improves model calibration, enhancing the reliability of the model's confidence estimates. Our findings underscore the importance of careful evaluation design and highlight the need for standardized, transparent evaluation protocols to ensure reliable and comparable results.

Question Answering systems these days typically use template-based language generation. Though adequate for a domain-specific task, these systems are too restrictive and predefined for domain-independent systems. This paper proposes a system that outputs a full-length answer given a question and the extracted factoid answer (short spans such as named entities) as the input. Our system uses constituency and dependency parse trees of questions. A transformer-based Grammar Error Correction model GECToR (2020), is used as a post-processing step for better fluency. We compare our system with (i) Modified Pointer Generator (SOTA) and (ii) Fine-tuned DialoGPT for factoid questions. We also test our approach on existential (yes-no) questions with better results. Our model generates accurate and fluent answers than the state-of-the-art (SOTA) approaches. The evaluation is done on NewsQA and SqUAD datasets with an increment of 0.4 and 0.9 percentage points in ROUGE-1 score respectively. Also the inference time is reduced by 85\% as compared to the SOTA. The improved datasets used for our evaluation will be released as part of the research contribution.

In precision-oriented tasks like answer ranking, it is more important to rank many relevant answers highly than to retrieve all relevant answers. It follows that a good ranking strategy would be to learn how to identify the easiest correct answers first (i.e., assign a high ranking score to answers that have characteristics that usually indicate relevance, and a low ranking score to those with characteristics that do not), before incorporating more complex logic to handle difficult cases (e.g., semantic matching or reasoning). In this work, we apply this idea to the training of neural answer rankers using curriculum learning. We propose several heuristics to estimate the difficulty of a given training sample. We show that the proposed heuristics can be used to build a training curriculum that down-weights difficult samples early in the training process. As the training process progresses, our approach gradually shifts to weighting all samples equally, regardless of difficulty. We present a comprehensive evaluation of our proposed idea on three answer ranking datasets. Results show that our approach leads to superior performance of two leading neural ranking architectures, namely BERT and ConvKNRM, using both pointwise and pairwise losses. When applied to a BERT-based ranker, our method yields up to a 4% improvement in MRR and a 9% improvement in P@1 (compared to the model trained without a curriculum). This results in models that can achieve comparable performance to more expensive state-of-the-art techniques.

Evaluation has traditionally focused on ranking candidates for a specific skill. Modern generalist models, such as Large Language Models (LLMs), decidedly outpace this paradigm. Open-ended evaluation systems, where candidate models are compared on user-submitted prompts, have emerged as a popular solution. Despite their many advantages, we show that the current Elo-based rating systems can be susceptible to and even reinforce biases in data, intentional or accidental, due to their sensitivity to redundancies. To address this issue, we propose evaluation as a 3-player game, and introduce novel game-theoretic solution concepts to ensure robustness to redundancy. We show that our method leads to intuitive ratings and provide insights into the competitive landscape of LLM development.

Large Language Models (LLMs) are increasingly relied upon to evaluate text outputs of other LLMs, thereby influencing leaderboards and development decisions. However, concerns persist over the accuracy of these assessments and the potential for misleading conclusions. In this work, we investigate the effectiveness of LLMs as evaluators for text generation tasks. We propose FBI, a novel framework designed to examine the proficiency of Evaluator LLMs in assessing four critical abilities in other LLMs: factual accuracy, instruction following, coherence in long-form writing, and reasoning proficiency. By introducing targeted perturbations in answers generated by LLMs, that clearly impact one of these key capabilities, we test whether an Evaluator LLM can detect these quality drops. By creating a total of 2400 perturbed answers covering 22 perturbation categories, we conduct a comprehensive study using different evaluation strategies on five prominent LLMs commonly used as evaluators in the literature. Our findings reveal significant shortcomings in current Evaluator LLMs, which failed to identify quality drops in over 50\% of cases on average. Single-answer and pairwise evaluations demonstrated notable limitations, whereas reference-based evaluations showed comparatively better performance. These results underscore the unreliable nature of current Evaluator LLMs and advocate for cautious implementation in practical applications. Code and data are available at https://github.com/AI4Bharat/FBI.

Abstention Ability (AA) is a critical aspect of Large Language Model (LLM) reliability, referring to an LLM's capability to withhold responses when uncertain or lacking a definitive answer, without compromising performance. Although previous studies have attempted to improve AA, they lack a standardised evaluation method and remain unsuitable for black-box models where token prediction probabilities are inaccessible. This makes comparative analysis challenging, especially for state-of-the-art closed-source commercial LLMs. This paper bridges this gap by introducing a black-box evaluation approach and a new dataset, Abstain-QA, crafted to rigorously assess AA across varied question types (answerable and unanswerable), domains (well-represented and under-represented), and task types (fact centric and reasoning). We also propose a new confusion matrix, the ''Answerable-Unanswerable Confusion Matrix'' (AUCM) which serves as the basis for evaluating AA, by offering a structured and precise approach for assessment. Finally, we explore the impact of three prompting strategies-Strict Prompting, Verbal Confidence Thresholding, and Chain-of-Thought (CoT)-on improving AA. Our results indicate that even powerful models like GPT-4, Mixtral 8x22b encounter difficulties with abstention; however, strategic approaches such as Strict prompting and CoT can enhance this capability.

The use of Large Language Models (LLMs) has increased significantly with users frequently asking questions to chatbots. In the time when information is readily accessible, it is crucial to stimulate and preserve human cognitive abilities and maintain strong reasoning skills. This paper addresses such challenges by promoting the use of hints as an alternative or a supplement to direct answers. We first introduce a manually constructed hint dataset, WikiHint, which is based on Wikipedia and includes 5,000 hints created for 1,000 questions. We then finetune open-source LLMs such as LLaMA-3.1 for hint generation in answer-aware and answeragnostic contexts. We assess the effectiveness of the hints with human participants who answer questions with and without the aid of hints. Additionally, we introduce a lightweight evaluation method, HintRank, to evaluate and rank hints in both answeraware and answer-agnostic settings. Our findings show that (a) the dataset helps generate more effective hints, (b) including answer information along with questions generally improves quality of generated hints, and (c) encoder-based models perform better than decoder-based models in hint ranking.

Scholastic trivia competitions test knowledge and intelligence through mastery of question answering. Modern question answering benchmarks are one variant of the Turing test. Specifically, answering a set of questions as well as a human is a minimum bar towards demonstrating human-like intelligence. This paper makes the case that the format of one competition -- where participants can answer in the middle of hearing a question (incremental) -- better differentiates the skill between (human or machine) players. Additionally, merging a sequential decision-making sub-task with question answering (QA) provides a good setting for research in model calibration and opponent modeling. Thus, embedded in this task are three machine learning challenges: (1) factoid QA over thousands of Wikipedia-like answers, (2) calibration of the QA model's confidence scores, and (3) sequential decision-making that incorporates knowledge of the QA model, its calibration, and what the opponent may do. We make two contributions: (1) collecting and curating a large factoid QA dataset and an accompanying gameplay dataset, and (2) developing a model that addresses these three machine learning challenges. In addition to offline evaluation, we pitted our model against some of the most accomplished trivia players in the world in a series of exhibition matches spanning several years. Throughout this paper, we show that collaborations with the vibrant trivia community have contributed to the quality of our dataset, spawned new research directions, and doubled as an exciting way to engage the public with research in machine learning and natural language processing.

Large Language Models (LLMs) have demonstrated considerable success in open-book question answering (QA), where the task requires generating answers grounded in a provided external context. A critical challenge in open-book QA is to ensure that model responses are based on the provided context rather than its parametric knowledge, which can be outdated, incomplete, or incorrect. Existing evaluation methods, primarily based on the LLM-as-a-judge approach, face significant limitations, including biases, scalability issues, and dependence on costly external systems. To address these challenges, we propose a novel metric that contrasts the perplexity of the model response under two conditions: when the context is provided and when it is not. The resulting score quantifies the extent to which the model's answer relies on the provided context. The validity of this metric is demonstrated through a series of experiments that show its effectiveness in identifying whether a given answer is grounded in the provided context. Unlike existing approaches, this metric is computationally efficient, interpretable, and adaptable to various use cases, offering a scalable and practical solution to assess context utilization in open-book QA systems.

Despite their sophisticated capabilities, large language models (LLMs) encounter a major hurdle in effective assessment. This paper first revisits the prevalent evaluation method-multiple choice question answering (MCQA), which allows for straightforward accuracy measurement. Through a comprehensive evaluation of 24 models across 11 benchmarks, we highlight several potential drawbacks of MCQA, for instance, the inconsistency between the MCQA evaluation and the generation of open-ended responses in practical scenarios. In response, we introduce an RWQ-Elo rating system, engaging 24 LLMs such as GPT-4, GPT-3.5, Google-Gemini-Pro and LLaMA-1/-2, in a two-player competitive format, with GPT-4 serving as the judge. Each LLM receives an Elo rating thereafter. This system is designed to mirror real-world usage, and for this purpose, we have compiled a new benchmark called ``Real-world questions'' (RWQ), comprising 20,772 authentic user inquiries. Additionally, we thoroughly analyze the characteristics of our system and compare it with prior leaderboards like AlpacaEval and MT-Bench. Our analysis reveals the stability of our RWQ-Elo system, the feasibility of registering new models, and its potential to reshape LLM leaderboards.

Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context. Binary scores and static rubrics fail to capture these context-dependent requirements. Existing methods define criteria at the dataset level or generate them in a single pass, which limits their ability to explore the evaluation space implied by each question. We introduce One-Question-One-World (Qworld), a method that generates question-specific evaluation criteria using a recursive expansion tree. Given a question, Qworld decomposes it into scenarios, perspectives, and fine-grained binary criteria through structured hierarchical and horizontal expansion. The resulting criteria specify what a high-quality answer must address for that question. On HealthBench, Qworld covers 89% of expert-authored criteria and generates 79% novel criteria validated by human experts. Experts rate Qworld criteria higher in insight and granularity than those produced by prior methods. When applied to 11 frontier LLMs on HealthBench and Humanity's Last Exam, Qworld reveals capability differences in dimensions such as long-term impact, equity, error handling, and interdisciplinary reasoning that coarse rubrics do not distinguish. By formulating criteria generation as structured coverage of question-implied evaluation axes, Qworld enables evaluation that adapts to each question rather than relying on fixed task-level criteria.

With the advancement of large language models (LLMs), their performance on multiple-choice question (MCQ) tasks has improved significantly. However, existing approaches face key limitations: answer choices are typically presented to LLMs without contextual grounding or explanation. This absence of context can lead to incomplete exploration of all possible answers, ultimately degrading the models' reasoning capabilities. To address these challenges, we introduce BiasPrompting, a novel inference framework that guides LLMs to generate and critically evaluate reasoning across all plausible answer options before reaching a final prediction. It consists of two components: first, a reasoning generation stage, where the model is prompted to produce supportive reasonings for each answer option, and then, a reasoning-guided agreement stage, where the generated reasonings are synthesized to select the most plausible answer. Through comprehensive evaluations, BiasPrompting demonstrates significant improvements in five widely used multiple-choice question answering benchmarks. Our experiments showcase that BiasPrompting enhances the reasoning capabilities of LLMs and provides a strong foundation for tackling complex and challenging questions, particularly in settings where existing methods underperform.

Can large language models improve without external data -- by generating their own questions and answers? We hypothesize that a pre-trained language model can improve its reasoning skills given only a single prompt specifying the topic (e.g., algebra word problems) and asking the model to generate its own questions. To do this, we propose Self-Questioning Language Models (SQLM): an asymmetric self-play framework where a proposer is given the topic and generates a question for a solver, who tries to answer it. Both the proposer and solver are trained via reinforcement learning. The proposer receives a reward if the problem is not too easy or too difficult, and the solver receives a reward based on majority voting, a proxy for correctness in the absence of ground-truth answers. For coding, the proposer can instead generate unit tests which are used for verification. We study this asymmetric self-play framework on three benchmarks: three-digit multiplication, algebra problems from the OMEGA benchmark, and programming problems from Codeforces. By continually generating more interesting problems and attempting to solve them, language models can improve on downstream benchmarks without access to any curated training datasets.

We propose Visual-only Question Answering (VoQA), a novel multimodal task in which questions are visually embedded within images, without any accompanying textual input. This requires models to locate, recognize, and reason over visually embedded textual questions, posing challenges for existing large vision-language models (LVLMs), which show notable performance drops even with carefully designed prompts. To bridge this gap, we introduce Guided Response Triggering Supervised Fine-tuning (GRT-SFT), a structured fine-tuning strategy that guides the model to perform step-by-step reasoning purely based on visual input, significantly improving model performance. Our work enhances models' capacity for human-like visual understanding in complex multimodal scenarios, where information, including language, is perceived visually.

The predictions of question answering (QA)systems are typically evaluated against manually annotated finite sets of one or more answers. This leads to a coverage limitation that results in underestimating the true performance of systems, and is typically addressed by extending over exact match (EM) with pre-defined rules or with the token-level F1 measure. In this paper, we present the first systematic conceptual and data-driven analysis to examine the shortcomings of token-level equivalence measures. To this end, we define the asymmetric notion of answer equivalence (AE), accepting answers that are equivalent to or improve over the reference, and publish over 23k human judgments for candidates produced by multiple QA systems on SQuAD. Through a careful analysis of this data, we reveal and quantify several concrete limitations of the F1 measure, such as a false impression of graduality, or missing dependence on the question. Since collecting AE annotations for each evaluated model is expensive, we learn a BERT matching (BEM) measure to approximate this task. Being a simpler task than QA, we find BEM to provide significantly better AE approximations than F1, and to more accurately reflect the performance of systems. Finally, we demonstrate the practical utility of AE and BEM on the concrete application of minimal accurate prediction sets, reducing the number of required answers by up to x2.6.

Given the widespread adoption and usage of Large Language Models (LLMs), it is crucial to have flexible and interpretable evaluations of their instruction-following ability. Preference judgments between model outputs have become the de facto evaluation standard, despite distilling complex, multi-faceted preferences into a single ranking. Furthermore, as human annotation is slow and costly, LLMs are increasingly used to make these judgments, at the expense of reliability and interpretability. In this work, we propose TICK (Targeted Instruct-evaluation with ChecKlists), a fully automated, interpretable evaluation protocol that structures evaluations with LLM-generated, instruction-specific checklists. We first show that, given an instruction, LLMs can reliably produce high-quality, tailored evaluation checklists that decompose the instruction into a series of YES/NO questions. Each question asks whether a candidate response meets a specific requirement of the instruction. We demonstrate that using TICK leads to a significant increase (46.4% to 52.2%) in the frequency of exact agreements between LLM judgements and human preferences, as compared to having an LLM directly score an output. We then show that STICK (Self-TICK) can be used to improve generation quality across multiple benchmarks via self-refinement and Best-of-N selection. STICK self-refinement on LiveBench reasoning tasks leads to an absolute gain of +7.8%, whilst Best-of-N selection with STICK attains +6.3% absolute improvement on the real-world instruction dataset, WildBench. In light of this, structured, multi-faceted self-improvement is shown to be a promising way to further advance LLM capabilities. Finally, by providing LLM-generated checklists to human evaluators tasked with directly scoring LLM responses to WildBench instructions, we notably increase inter-annotator agreement (0.194 to 0.256).

ARC Challenge appears more difficult than ARC Easy for modern LLMs primarily due to an evaluation setup that prevents direct comparison of answer choices rather than inherent complexity. Although some researchers have quietly shifted to a more appropriate scheme over the last year, the implications of this change have yet to be widely acknowledged. We highlight this overlooked shift, show how similar evaluation practices falsely imply reasoning deficits in other benchmarks, and demonstrate that fairer methods dramatically reduce performance gaps (e.g. on SIQA) and even yield superhuman results (OpenBookQA). In doing so, we reveal how evaluation shapes perceived difficulty and offer guidelines to ensure that multiple-choice evaluations accurately reflect actual model capabilities.

Large Language Models (LLMs) have demonstrated significant capabilities, particularly in the domain of question answering (QA). However, their effectiveness in QA is often undermined by the vagueness of user questions. To address this issue, we introduce single-round instance-level prompt optimization, referred to as question rewriter. By enhancing the intelligibility of human questions for black-box LLMs, our question rewriter improves the quality of generated answers. The rewriter is optimized using direct preference optimization based on feedback collected from automatic criteria for evaluating generated answers; therefore, its training does not require costly human annotations. The experiments across multiple black-box LLMs and long-form question answering (LFQA) datasets demonstrate the efficacy of our method. This paper provides a practical framework for training question rewriters and sets a precedent for future explorations in prompt optimization within LFQA tasks. Code is available at https://github.com/3244we/Question-Rewriter.

The continuous advancement of large language models (LLMs) has brought increasing attention to the critical issue of developing fair and reliable methods for evaluating their performance. Particularly, the emergence of cheating phenomena, such as test set leakage and prompt format overfitting, poses significant challenges to the reliable evaluation of LLMs. As evaluation frameworks commonly use Regular Expression (RegEx) for answer extraction, models may adjust their responses to fit formats easily handled by RegEx. Nevertheless, the key answer extraction module based on RegEx frequently suffers from extraction errors. Furthermore, recent studies proposing fine-tuned LLMs as judge models for automated evaluation face challenges in terms of generalization ability and fairness. This paper comprehensively analyzes the entire LLM evaluation chain and demonstrates that optimizing the key answer extraction module improves extraction accuracy and enhances evaluation reliability. Our findings suggest that improving the key answer extraction module can lead to higher judgment accuracy and improved evaluation efficiency compared to the judge models. To address these issues, we propose xFinder, a novel evaluator for answer extraction and matching in LLM evaluation. As part of this process, we create a specialized dataset, the Key Answer Finder (KAF) dataset, to ensure effective model training and evaluation. Generalization tests and real-world evaluations show that the smallest xFinder model, with only 500 million parameters, achieves an average extraction accuracy of 93.42\%. In contrast, RegEx accuracy in the best evaluation framework is 74.38\%. The final judgment accuracy of xFinder reaches 97.61\%, outperforming existing evaluation frameworks and judge models.

While question-answering~(QA) benchmark performance is an automatic and scalable method to compare LLMs, it is an indirect method of evaluating their underlying problem-solving capabilities. Therefore, we propose a holistic and generalizable framework based on cascaded question disclosure that provides a more accurate estimate of the models' problem-solving capabilities while maintaining the scalability and automation. This approach collects model responses in a stagewise manner with each stage revealing partial information about the question designed to elicit generalized reasoning in LLMs. We find that our approach not only provides a better comparison between LLMs, but also induces better intermediate traces in models compared to the standard QA paradigm. We empirically verify this behavior on diverse reasoning and knowledge-heavy QA datasets by comparing LLMs of varying sizes and families. Our approach narrows the performance gap observed in the standard QA evaluation settings, indicating that the prevalent indirect QA paradigm of evaluation overestimates the differences in performance between models. We further validate our findings by extensive ablation studies.

Model-based evaluation is at the heart of successful model development -- as a reward model for training, and as a replacement for human evaluation. To train such evaluators, the standard approach is to collect a large amount of human preference judgments over model responses, which is costly and the data becomes stale as models improve. In this work, we present an approach that aims to im-prove evaluators without human annotations, using synthetic training data only. Starting from unlabeled instructions, our iterative self-improvement scheme generates contrasting model outputs and trains an LLM-as-a-Judge to produce reasoning traces and final judgments, repeating this training at each new iteration using the improved predictions. Without any labeled preference data, our Self-Taught Evaluator can improve a strong LLM (Llama3-70B-Instruct) from 75.4 to 88.3 (88.7 with majority vote) on RewardBench. This outperforms commonly used LLM judges such as GPT-4 and matches the performance of the top-performing reward models trained with labeled examples.

Large language models (LLMs) are increasingly evaluated on single-answer multiple-choice tasks, yet many real-world problems require identifying all correct answers from a set of options. This capability remains underexplored. We introduce SATA-BENCH, the first dedicated benchmark for evaluating LLMs on Select All That Apply (SATA) questions across diverse domains, including reading comprehension, law, and biomedicine. Our evaluation of 27 open-source and proprietary models reveals a significant gap: even the strongest model achieves only 41.8% exact match, exposing LLMs' inability to reliably identify all correct answers. We find that this weakness stems from two core challenges: selection bias - models favor certain choices regardless of content, and count bias - models fail to predict the correct number of answers. To address these issues, we propose Choice Funnel, a decoding strategy that combines token debiasing with adaptive thresholding to guide models toward complete and accurate selections. Choice Funnel achieves up to 29% higher exact match than competitive baselines while reducing inference cost by over 64%. Our findings expose fundamental limitations in current LLMs and introduce a new framework for diagnosing and improving multi-answer reasoning. We release SATA-BENCH and Choice Funnel to promote LLM development for robust decision-making in realistic, multi-answer applications.

Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the structured evidence of knowledge graphs. However, current evaluation practices fall short: existing benchmarks often include questions that can be directly answered using existing triples in KG, making it unclear whether models perform reasoning or simply retrieve answers directly. Moreover, inconsistent evaluation metrics and lenient answer matching criteria further obscure meaningful comparisons. In this work, we introduce a general method for constructing benchmarks, together with an evaluation protocol, to systematically assess KG-RAG methods under knowledge incompleteness. Our empirical results show that current KG-RAG methods have limited reasoning ability under missing knowledge, often rely on internal memorization, and exhibit varying degrees of generalization depending on their design.

Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. We argue that both are suboptimal, since gold evidence is not always available, and QA is fundamentally different from IR. We show for the first time that it is possible to jointly learn the retriever and reader from question-answer string pairs and without any IR system. In this setting, evidence retrieval from all of Wikipedia is treated as a latent variable. Since this is impractical to learn from scratch, we pre-train the retriever with an Inverse Cloze Task. We evaluate on open versions of five QA datasets. On datasets where the questioner already knows the answer, a traditional IR system such as BM25 is sufficient. On datasets where a user is genuinely seeking an answer, we show that learned retrieval is crucial, outperforming BM25 by up to 19 points in exact match.

Building training-ready multi-hop question answering (QA) datasets that truly stress a model's retrieval and reasoning abilities remains highly challenging recently. While there have been a few recent evaluation datasets that capture the characteristics of hard-to-search but easy-to-verify problems -- requiring the integration of ambiguous, indirect, and cross-domain cues -- these data resources remain scarce and are mostly designed for evaluation, making them unsuitable for supervised fine-tuning (SFT) or reinforcement learning (RL). Meanwhile, manually curating non-trivially retrievable questions -- where answers cannot be found through a single direct query but instead require multi-hop reasoning over oblique and loosely connected evidence -- incurs prohibitive human costs and fails to scale, creating a critical data bottleneck for training high-capability retrieval-and-reasoning agents. To address this, we present an automated framework for generating high-difficulty, training-ready multi-hop questions from semi-structured knowledge sources. The system (i) grows diverse, logically labeled evidence clusters through Natural Language Inference (NLI)-based relation typing and diversity-aware expansion; (ii) applies reverse question construction to compose oblique cues so that isolated signals are underinformative but their combination uniquely identifies the target entity; and (iii) enforces quality with a two-step evaluation pipeline that combines multi-model consensus filtering with structured constraint decomposition and evidence-based matching. The result is a scalable process that yields complex, retrieval-resistant yet verifiable questions suitable for SFT/RL training as well as challenging evaluation, substantially reducing human curation effort while preserving the difficulty profile of strong evaluation benchmarks.

As large language models (LLMs) grow larger and more sophisticated, assessing their "reasoning" capabilities in natural language grows more challenging. Recent question answering (QA) benchmarks that attempt to assess reasoning are often limited by a narrow scope of covered situations and subject matters. We introduce WikiWhy, a QA dataset built around a novel auxiliary task: explaining why an answer is true in natural language. WikiWhy contains over 9,000 "why" question-answer-rationale triples, grounded on Wikipedia facts across a diverse set of topics. Each rationale is a set of supporting statements connecting the question to the answer. WikiWhy serves as a benchmark for the reasoning capabilities of LLMs because it demands rigorous explicit rationales for each answer to demonstrate the acquisition of implicit commonsense knowledge, which is unlikely to be easily memorized. GPT-3 baselines achieve only 38.7% human-evaluated correctness in the end-to-end answer & explain condition, leaving significant room for future improvements.

In current NLP research, large-scale language models and their abilities are widely being discussed. Some recent works have also found notable failures of these models. Often these failure examples involve complex reasoning abilities. This work focuses on a simple commonsense ability, reasoning about when an action (or its effect) is feasible. To this end, we introduce FeasibilityQA, a question-answering dataset involving binary classification (BCQ) and multi-choice multi-correct questions (MCQ) that test understanding of feasibility. We show that even state-of-the-art models such as GPT-3, GPT-2, and T5 struggle to answer the feasibility questions correctly. Specifically, on MCQ and BCQ questions, GPT-3 achieves an accuracy of just (19%, 62%) and (25%, 64%) in zero-shot and few-shot settings, respectively. We also evaluate models by providing relevant knowledge statements required to answer the question. We find that the additional knowledge leads to a 7% gain in performance, but the overall performance still remains low. These results make one wonder how much commonsense knowledge about action feasibility is encoded in state-of-the-art models and how well they can reason about it.

The performance of large language models (LLMs) on existing reasoning benchmarks has significantly improved over the past years. In response, we present JEEBench, a considerably more challenging benchmark dataset for evaluating the problem solving abilities of LLMs. We curate 515 challenging pre-engineering mathematics, physics and chemistry problems from the highly competitive IIT JEE-Advanced exam. Long-horizon reasoning on top of deep in-domain knowledge is essential for solving problems in this benchmark. Our evaluation on various open-source and proprietary models reveals that the highest performance, even after using techniques like self-consistency, self-refinement and chain-of-thought prompting, is less than 40%. The typical failure modes of GPT-4, the best model, are errors in algebraic manipulation, difficulty in grounding abstract concepts into mathematical equations accurately and failure in retrieving relevant domain-specific concepts. We also observe that by mere prompting, GPT-4 is unable to assess risk introduced by negative marking for incorrect answers. For this, we develop a post-hoc confidence-thresholding method over self-consistency, which enables effective response selection. We hope that our challenging benchmark will guide future re-search in problem-solving using LLMs.

One of the most widely used tasks to evaluate Large Language Models (LLMs) is Multiple-Choice Question Answering (MCQA). While open-ended question answering tasks are more challenging to evaluate, MCQA tasks are, in principle, easier to assess, as the model's answer is thought to be simple to extract and is directly compared to a set of predefined choices. However, recent studies have started to question the reliability of MCQA evaluation, showing that multiple factors can significantly impact the reported performance of LLMs, especially when the model generates free-form text before selecting one of the answer choices. In this work, we shed light on the inconsistencies of MCQA evaluation strategies, which can lead to inaccurate and misleading model comparisons. We systematically analyze whether existing answer extraction methods are aligned with human judgment, and how they are influenced by answer constraints in the prompt across different domains. Our experiments demonstrate that traditional evaluation strategies often underestimate LLM capabilities, while LLM-based answer extractors are prone to systematic errors. Moreover, we reveal a fundamental trade-off between including format constraints in the prompt to simplify answer extraction and allowing models to generate free-form text to improve reasoning. Our findings call for standardized evaluation methodologies and highlight the need for more reliable and consistent MCQA evaluation practices.

Recent advancements in reinforcement learning (RL) for large language models (LLMs), exemplified by DeepSeek R1, have shown that even a simple question-answering task can substantially improve an LLM's reasoning capabilities. In this work, we extend this approach by modifying the task into a multi-attempt setting. Instead of generating a single response per question, the model is given multiple attempts, with feedback provided after incorrect responses. The multi-attempt task encourages the model to refine its previous attempts and improve search efficiency. Experimental results show that even a small LLM trained on a multi-attempt task achieves significantly higher accuracy when evaluated with more attempts, improving from 45.6% with 1 attempt to 52.5% with 2 attempts on the math benchmark. In contrast, the same LLM trained on a standard single-turn task exhibits only a marginal improvement, increasing from 42.3% to 43.2% when given more attempts during evaluation. The results indicate that, compared to the standard single-turn task, an LLM trained on a multi-attempt task achieves slightly better performance on math benchmarks while also learning to refine its responses more effectively based on user feedback. Full code is available at https://github.com/DualityRL/multi-attempt

Solving algebraic word problems requires executing a series of arithmetic operations---a program---to obtain a final answer. However, since programs can be arbitrarily complicated, inducing them directly from question-answer pairs is a formidable challenge. To make this task more feasible, we solve these problems by generating answer rationales, sequences of natural language and human-readable mathematical expressions that derive the final answer through a series of small steps. Although rationales do not explicitly specify programs, they provide a scaffolding for their structure via intermediate milestones. To evaluate our approach, we have created a new 100,000-sample dataset of questions, answers and rationales. Experimental results show that indirect supervision of program learning via answer rationales is a promising strategy for inducing arithmetic programs.

Subjective Answer Grading (SAG) plays a crucial role in education, standardized testing, and automated assessment systems, particularly for evaluating short-form responses in Short Answer Scoring (SAS). However, existing approaches often produce coarse-grained scores and lack detailed reasoning. Although large language models (LLMs) have demonstrated potential as zero-shot evaluators, they remain susceptible to bias, inconsistencies with human judgment, and limited transparency in scoring decisions. To overcome these limitations, we introduce SAS-Bench, a benchmark specifically designed for LLM-based SAS tasks. SAS-Bench provides fine-grained, step-wise scoring, expert-annotated error categories, and a diverse range of question types derived from real-world subject-specific exams. This benchmark facilitates detailed evaluation of model reasoning processes and explainability. We also release an open-source dataset containing 1,030 questions and 4,109 student responses, each annotated by domain experts. Furthermore, we conduct comprehensive experiments with various LLMs, identifying major challenges in scoring science-related questions and highlighting the effectiveness of few-shot prompting in improving scoring accuracy. Our work offers valuable insights into the development of more robust, fair, and educationally meaningful LLM-based evaluation systems.

Despite extensive research on a wide range of question answering (QA) systems, most existing work focuses on answer containment-i.e., assuming that answers can be directly extracted and/or generated from documents in the corpus. However, some questions require inference, i.e., deriving answers that are not explicitly stated but can be inferred from the available information. We introduce Inferential QA -- a new task that challenges models to infer answers from answer-supporting passages which provide only clues. To study this problem, we construct QUIT (QUestions requiring Inference from Texts) dataset, comprising 7,401 questions and 2.4M passages built from high-convergence human- and machine-authored hints, labeled across three relevance levels using LLM-based answerability and human verification. Through comprehensive evaluation of retrievers, rerankers, and LLM-based readers, we show that methods effective on traditional QA tasks struggle in inferential QA: retrievers underperform, rerankers offer limited gains, and fine-tuning provides inconsistent improvements. Even reasoning-oriented LLMs fail to outperform smaller general-purpose models. These findings reveal that current QA pipelines are not yet ready for inference-based reasoning. Inferential QA thus establishes a new class of QA tasks that move towards understanding and reasoning from indirect textual evidence.

While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, growing evidence suggests much of their success stems from memorized answer-reasoning patterns rather than genuine inference. In this work, we investigate a central question: are LLMs primarily anchored to final answers or to the textual pattern of reasoning chains? We propose a five-level answer-visibility prompt framework that systematically manipulates answer cues and probes model behavior through indirect, behavioral analysis. Experiments across state-of-the-art LLMs reveal a strong and consistent reliance on explicit answers. The performance drops by 26.90\% when answer cues are masked, even with complete reasoning chains. These findings suggest that much of the reasoning exhibited by LLMs may reflect post-hoc rationalization rather than true inference, calling into question their inferential depth. Our study uncovers the answer-anchoring phenomenon with rigorous empirical validation and underscores the need for a more nuanced understanding of what constitutes reasoning in LLMs.

Despite the remarkable coherence of Large Language Models (LLMs), existing evaluation methods often suffer from fluency bias and rely heavily on multiple-choice formats, making it difficult to assess factual accuracy and complex reasoning effectively. LLMs thus frequently generate factually inaccurate responses, especially in complex reasoning tasks, highlighting two prominent challenges: (1) the inadequacy of existing methods to evaluate reasoning and factual accuracy effectively, and (2) the reliance on human evaluators for nuanced judgment, as illustrated by Williams and Huckle (2024)[1], who found manual grading indispensable despite automated grading advancements. To address evaluation gaps in open-ended reasoning tasks, we introduce the EQUATOR Evaluator (Evaluation of Question Answering Thoroughness in Open-ended Reasoning). This framework combines deterministic scoring with a focus on factual accuracy and robust reasoning assessment. Using a vector database, EQUATOR pairs open-ended questions with human-evaluated answers, enabling more precise and scalable evaluations. In practice, EQUATOR significantly reduces reliance on human evaluators for scoring and improves scalability compared to Williams and Huckle's (2004)[1] methods. Our results demonstrate that this framework significantly outperforms traditional multiple-choice evaluations while maintaining high accuracy standards. Additionally, we introduce an automated evaluation process leveraging smaller, locally hosted LLMs. We used LLaMA 3.2B, running on the Ollama binaries to streamline our assessments. This work establishes a new paradigm for evaluating LLM performance, emphasizing factual accuracy and reasoning ability, and provides a robust methodological foundation for future research.

For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecified, ill-posed, or fundamentally unanswerable, require LLMs to reason about uncertainty and selectively abstain -- i.e., refuse to answer definitively. However, abstention remains understudied, without a systematic evaluation framework for modern LLMs. In this work, we introduce AbstentionBench, a large-scale benchmark for holistically evaluating abstention across 20 diverse datasets, including questions with unknown answers, underspecification, false premises, subjective interpretations, and outdated information. Evaluating 20 frontier LLMs reveals abstention is an unsolved problem, and one where scaling models is of little use. While recent reasoning LLMs have shown impressive results in complex problem solving, surprisingly, we find that reasoning fine-tuning degrades abstention (by 24% on average), even for math and science domains on which reasoning models are explicitly trained. We find that while a carefully crafted system prompt can boost abstention in practice, it does not resolve models' fundamental inability to reason about uncertainty. We release AbstentionBench to foster research into advancing LLM reliability.

We present the ARC-DA dataset, a direct-answer ("open response", "freeform") version of the ARC (AI2 Reasoning Challenge) multiple-choice dataset. While ARC has been influential in the community, its multiple-choice format is unrepresentative of real-world questions, and multiple choice formats can be particularly susceptible to artifacts. The ARC-DA dataset addresses these concerns by converting questions to direct-answer format using a combination of crowdsourcing and expert review. The resulting dataset contains 2985 questions with a total of 8436 valid answers (questions typically have more than one valid answer). ARC-DA is one of the first DA datasets of natural questions that often require reasoning, and where appropriate question decompositions are not evident from the questions themselves. We describe the conversion approach taken, appropriate evaluation metrics, and several strong models. Although high, the best scores (81% GENIE, 61.4% F1, 63.2% ROUGE-L) still leave considerable room for improvement. In addition, the dataset provides a natural setting for new research on explanation, as many questions require reasoning to construct answers. We hope the dataset spurs further advances in complex question-answering by the community. ARC-DA is available at https://allenai.org/data/arc-da

Reinforcement learning (RL) has become a key component in training large language reasoning models (LLMs). However, recent studies questions its effectiveness in improving multi-step reasoning-particularly on hard problems. To address this challenge, we propose a simple yet effective strategy via Question Augmentation: introduce partial solutions during training to reduce problem difficulty and provide more informative learning signals. Our method, QuestA, when applied during RL training on math reasoning tasks, not only improves pass@1 but also pass@k-particularly on problems where standard RL struggles to make progress. This enables continual improvement over strong open-source models such as DeepScaleR and OpenMath Nemotron, further enhancing their reasoning capabilities. We achieve new state-of-the-art results on math benchmarks using 1.5B-parameter models: 67.1% (+5.3%) on AIME24, 59.5% (+10.0%) on AIME25, and 35.5% (+4.0%) on HMMT25. Further, we provide theoretical explanations that QuestA improves sample efficiency, offering a practical and generalizable pathway for expanding reasoning capability through RL.

We introduce a benchmark for open-ended regional question answering that encompasses both textual and visual modalities. We also provide strong baselines using state-of-the-art large language models (LLMs). Our dataset consists of manually curated questions and answers grounded in Wikipedia, created by native speakers from Czechia, Slovakia, and Ukraine, with accompanying English translations. It includes both purely textual questions and those requiring visual understanding. As a baseline, we evaluate state-of-the-art LLMs through prompting and complement this with human judgments of answer correctness. Using these human evaluations, we analyze the reliability of existing automatic evaluation metrics. Our baseline results highlight a significant gap in regional knowledge among current LLMs. Moreover, apart from LLM-based evaluation, there is minimal correlation between automated metrics and human judgment. We release this dataset as a resource to (1) assess regional knowledge in LLMs, (2) study cross-lingual generation consistency in a challenging setting, and (3) advance the development of evaluation metrics for open-ended question answering.

The automatic generation of Multiple Choice Questions (MCQ) has the potential to reduce the time educators spend on student assessment significantly. However, existing evaluation metrics for MCQ generation, such as BLEU, ROUGE, and METEOR, focus on the n-gram based similarity of the generated MCQ to the gold sample in the dataset and disregard their educational value. They fail to evaluate the MCQ's ability to assess the student's knowledge of the corresponding target fact. To tackle this issue, we propose a novel automatic evaluation metric, coined Knowledge Dependent Answerability (KDA), which measures the MCQ's answerability given knowledge of the target fact. Specifically, we first show how to measure KDA based on student responses from a human survey. Then, we propose two automatic evaluation metrics, KDA_disc and KDA_cont, that approximate KDA by leveraging pre-trained language models to imitate students' problem-solving behavior. Through our human studies, we show that KDA_disc and KDA_soft have strong correlations with both (1) KDA and (2) usability in an actual classroom setting, labeled by experts. Furthermore, when combined with n-gram based similarity metrics, KDA_disc and KDA_cont are shown to have a strong predictive power for various expert-labeled MCQ quality measures.

With significant efforts in recent studies, LLM-as-a-Judge has become a cost-effective alternative to human evaluation for assessing the text generation quality in a wide range of tasks. However, there still remains a reliability gap between LLM-as-a-Judge and human evaluation. One important reason is the lack of guided oracles in the evaluation process. Motivated by the role of reference pervasively used in classic text evaluation, we introduce RevisEval, a novel text generation evaluation paradigm via the response-adapted references. RevisEval is driven by the key observation that an ideal reference should maintain the necessary relevance to the response to be evaluated. Specifically, RevisEval leverages the text revision capabilities of large language models (LLMs) to adaptively revise the response, then treat the revised text as the reference (response-adapted reference) for the subsequent evaluation. Extensive experiments demonstrate that RevisEval outperforms traditional reference-free and reference-based evaluation paradigms that use LLM-as-a-Judge across NLG tasks and open-ended instruction-following tasks. More importantly, our response-adapted references can further boost the classical text metrics, e.g., BLEU and BERTScore, compared to traditional references and even rival the LLM-as-a-Judge. A detailed analysis is also conducted to confirm RevisEval's effectiveness in bias reduction, the impact of inference cost, and reference relevance.

Retrieval-augmented generation (RAG) is considered to be a promising approach to alleviate the hallucination issue of large language models (LLMs), and it has received widespread attention from researchers recently. Due to the limitation in the semantic understanding of retrieval models, the success of RAG heavily lies on the ability of LLMs to identify passages with utility. Recent efforts have explored the ability of LLMs to assess the relevance of passages in retrieval, but there has been limited work on evaluating the utility of passages in supporting question answering. In this work, we conduct a comprehensive study about the capabilities of LLMs in utility evaluation for open-domain QA. Specifically, we introduce a benchmarking procedure and collection of candidate passages with different characteristics, facilitating a series of experiments with five representative LLMs. Our experiments reveal that: (i) well-instructed LLMs can distinguish between relevance and utility, and that LLMs are highly receptive to newly generated counterfactual passages. Moreover, (ii) we scrutinize key factors that affect utility judgments in the instruction design. And finally, (iii) to verify the efficacy of utility judgments in practical retrieval augmentation applications, we delve into LLMs' QA capabilities using the evidence judged with utility and direct dense retrieval results. (iv) We propose a k-sampling, listwise approach to reduce the dependency of LLMs on the sequence of input passages, thereby facilitating subsequent answer generation. We believe that the way we formalize and study the problem along with our findings contributes to a critical assessment of retrieval-augmented LLMs. Our code and benchmark can be found at https://github.com/ict-bigdatalab/utility_judgments.

Large Language Models (LLMs) leverage step-by-step reasoning to solve complex problems. Standard evaluation practice involves generating a complete reasoning trace and assessing the correctness of the final answer presented at its conclusion. In this paper, we challenge the reliance on the final answer by posing the following two questions: Does the final answer reliably represent the model's optimal conclusion? Can alternative reasoning paths yield different results? To answer these questions, we analyze intermediate reasoning steps, termed subthoughts, and propose a method based on our findings. Our approach involves segmenting a reasoning trace into sequential subthoughts based on linguistic cues. We start by prompting the model to generate continuations from the end-point of each intermediate subthought. We extract a potential answer from every completed continuation originating from different subthoughts. We find that aggregating these answers by selecting the most frequent one (the mode) often yields significantly higher accuracy compared to relying solely on the answer derived from the original complete trace. Analyzing the consistency among the answers derived from different subthoughts reveals characteristics that correlate with the model's confidence and correctness, suggesting potential for identifying less reliable answers. Our experiments across various LLMs and challenging mathematical reasoning datasets (AIME2024 and AIME2025) show consistent accuracy improvements, with gains reaching up to 13\% and 10\% respectively. Implementation is available at: https://github.com/hammoudhasan/SubthoughtReasoner.

Automated answer matching, which leverages LLMs to evaluate free-text responses by comparing them to a reference answer, shows substantial promise as a scalable and aligned alternative to human evaluation. However, its reliability requires robustness against strategic attacks such as guesswork or verbosity that may artificially inflate scores without improving actual correctness. In this work, we systematically investigate whether such tactics deceive answer matching models by prompting examinee models to: (1) generate verbose responses, (2) provide multiple answers when unconfident, and (3) embed conflicting answers with the correct answer near the start of their response. Our results show that these manipulations do not increase scores and often reduce them. Additionally, binary scoring (which requires a matcher to answer with a definitive "correct" or "incorrect") is more robust to attacks than continuous scoring (which requires a matcher to determine partial correctness). These findings show that answer matching is generally robust to inexpensive text manipulation and is a viable alternative to traditional LLM-as-a-judge or human evaluation when reference answers are available.

Large Language Models (LLMs) are revolutionizing information retrieval, with chatbots becoming an important source for answering user queries. As by their design, LLMs prioritize generating correct answers, the value of highly plausible yet incorrect answers (candidate answers) tends to be overlooked. However, such answers can still prove useful, for example, they can play a crucial role in tasks like Multiple-Choice Question Answering (MCQA) and QA Robustness Assessment (QARA). Existing QA datasets primarily focus on correct answers without explicit consideration of the plausibility of other candidate answers, limiting opportunity for more nuanced evaluations of models. To address this gap, we introduce PlausibleQA, a large-scale dataset comprising 10,000 questions and 100,000 candidate answers, each annotated with plausibility scores and justifications for their selection. Additionally, the dataset includes 900,000 justifications for pairwise comparisons between candidate answers, further refining plausibility assessments. We evaluate PlausibleQA through human assessments and empirical experiments, demonstrating its utility in MCQA and QARA analysis. Our findings show that plausibility-aware approaches are effective for MCQA distractor generation and QARA. We release PlausibleQA as a resource for advancing QA research and enhancing LLM performance in distinguishing plausible distractors from correct answers.

Large Language Models (LLMs) have shown remarkable capabilities across tasks, yet they often require additional prompting techniques when facing complex problems. While approaches like self-correction and response selection have emerged as popular solutions, recent studies have shown these methods perform poorly when relying on the LLM itself to provide feedback or selection criteria. We argue this limitation stems from the fact that common LLM post-training procedures lack explicit supervision for discriminative judgment tasks. In this paper, we propose Generative Self-Aggregation (GSA), a novel prompting method that improves answer quality without requiring the model's discriminative capabilities. GSA first samples multiple diverse responses from the LLM, then aggregates them to obtain an improved solution. Unlike previous approaches, our method does not require the LLM to correct errors or compare response quality; instead, it leverages the model's generative abilities to synthesize a new response based on the context of multiple samples. While GSA shares similarities with the self-consistency (SC) approach for response aggregation, SC requires specific verifiable tokens to enable majority voting. In contrast, our approach is more general and can be applied to open-ended tasks. Empirical evaluation demonstrates that GSA effectively improves response quality across various tasks, including mathematical reasoning, knowledge-based problems, and open-ended generation tasks such as code synthesis and conversational responses.

Recent advances in Large Language Models (LLMs) and Reinforcement Learning (RL) have led to strong performance in open-domain question answering (QA). However, existing models still struggle with questions that admit multiple valid answers. Standard QA benchmarks, which typically assume a single gold answer, overlook this reality and thus produce inappropriate training signals. Existing attempts to handle ambiguity often rely on costly manual annotation, which is difficult to scale to multi-hop datasets such as HotpotQA and MuSiQue. In this paper, we present A^2Search, an annotation-free, end-to-end training framework to recognize and handle ambiguity. At its core is an automated pipeline that detects ambiguous questions and gathers alternative answers via trajectory sampling and evidence verification. The model is then optimized with RL using a carefully designed AnsF1 reward, which naturally accommodates multiple answers. Experiments on eight open-domain QA benchmarks demonstrate that A^2Search achieves new state-of-the-art performance. With only a single rollout, A^2Search-7B yields an average AnsF1@1 score of 48.4% across four multi-hop benchmarks, outperforming all strong baselines, including the substantially larger ReSearch-32B (46.2%). Extensive analyses further show that A^2Search resolves ambiguity and generalizes across benchmarks, highlighting that embracing ambiguity is essential for building more reliable QA systems. Our code, data, and model weights can be found at https://github.com/zfj1998/A2Search