text string | source string |
|---|---|
0.8282 0.8182 0.9059 Xgboost 0.9153 0.8676 0.8963 0.8807 0.9740 Deep Learning RNN 0.8290 0.8474 0.6273 0.7181 0.8742 Bilstm 0.8384 0.8798 0.6263 0.7297 0.8843 Bilstm -Attention 0.8422 0.8887 0.6306 0.7364 0.8760 Roberta Machine Learning RF 0.7849 0.7985 0.8046 0.7972 0.8775 SVM 0.7864 0.7939 0.8151 0.8004 0.8665 Logist... | https://arxiv.org/abs/2505.17380v1 |
developed a computational evaluation framework. Initially, the global SHAP method was employed for sensitivity analysis and local SHAP method for feature pruning, leading to the construct ion of a more refined predictive model. These results were then integrated with relevant theoretical paradigms to establish a compre... | https://arxiv.org/abs/2505.17380v1 |
13 Warn substances Negative 0.434961 14 Raise Concern (without permission) discrepancy Negative 0.39475 15 Negotiation LSM Negative 0.35326 16 Structure time Negative 0.261476 17 Warn Physical Negative 0.182461 As present ed in Table V, t hese intrinsic metrics were aligned with the MI dimensions from existing literatu... | https://arxiv.org/abs/2505.17380v1 |
1.746483 First, as illustrated in Table VI, although GPT -4’s overall performance on intrinsic metrics marginally lagged behind that of human therapists, it exhibited a distinct advantage in the MIIN behaviors. Specifically, GPT -4 outperformed human therapists in “Advice (without permission)” dimension (Cohen’s d = –0... | https://arxiv.org/abs/2505.17380v1 |
in its linguistic cue sand MI strategies, given that these foundational metrics constitute the cornerstone for meaningful advancements in both overall assessment outcomes and therapeutic effectiveness. These results address RQ2. C. Validation of the Integrative computational Evaluation Framework To validate the pivotal... | https://arxiv.org/abs/2505.17380v1 |
based on the computational evaluat ion framework. Leveraging a CoT methodology, the customized prompt was systematically integrated with the original RACE prompt to create a tailored zero -shot prompt. Comprehensive details regarding both the original and customized prompts are provided in s upplementary materials. 2) ... | https://arxiv.org/abs/2505.17380v1 |
(0.136***) discussions, reflecting higher levels of empathy. Additionally, a marked reduction in “Apostrophes ” (-0.732***) contributed to enhanced professionalism. Furthermore, the decrease in LSM (-0.145***) facilitated improvements in UPQ scores. At the same time, the reduction in the use of “Articles” ( -0.147***) ... | https://arxiv.org/abs/2505.17380v1 |
the methodologies employed in this study effectively enhanced the LLM’s MI performance while ensuring transparency and interpretability of the optimization process. The comprehensive computational evaluation framework combined the extrinsic metric with intrinsic metrics, revealing the intricate relationship between the... | https://arxiv.org/abs/2505.17380v1 |
- quali ty MI sessions [106] . Moreover, the incorporation of perception -related terminology heightens empathy, as it allo ws therapists to accurately reflect the client’s lived experiences, thus enhancing self -reflection and motivation [107], [108], [109], [110] . On the negative side, however, GPT -4 may also over-... | https://arxiv.org/abs/2505.17380v1 |
promising preliminary exploration toward achieving this objective. Based on the UPQ -centered evaluation, it is evident that GPT -4 can further optimiz e its Simple Reflections, empathic expressions, and professional communication style to align more closely with core MI principles (e.g., avoiding unsolicited advice an... | https://arxiv.org/abs/2505.17380v1 |
Comparative analysis further revealed that an excessive reliance on informal language diminished the perceived professionalism of the LLM, whereas an overemphasis on analytical thinking exacerbated emotional detachment from clients. To mitigate these issues, the LLM should limit the use of apostrophes to enhance its pr... | https://arxiv.org/abs/2505.17380v1 |
more comprehensive and high -fidelity LLM behavior evaluation frameworks in psychotherapy. Secondly, since the introduction of Eliza, a simulated psychotherapist [134] , in the 1960s, the concept of therapy chatbots offering mental health support has consistently attracted the interest of clinicians, researchers, and t... | https://arxiv.org/abs/2505.17380v1 |
bias and discrimination are key ethical considerations. The training data used for LLM may contain inherent biases, which could be amplified during the model’s analysis and generation process [137], [138], [139] . In the context of MI, such biases could result in misunderstand ings or unfair treatment of specific group... | https://arxiv.org/abs/2505.17380v1 |
: arXiv:2307.09288. doi: 10.48550/arXiv.2307.09288. [5] S. Bubeck et al. , Sparks of A rtificial General Intelligence: Early experiments with GPT -4. 2023. doi: 10.48550/arXiv.2303.12712. [6] X. Sun et al. , “Eliciting Motivational Interviewing Skill Codes in Psychotherapy with LLMs: Joint 30th International Conference... | https://arxiv.org/abs/2505.17380v1 |
S. R. Pendse, and N. Kumar, “Benefits and Harms of Large Language Models in Digital Mental Health,” Nov. 07, 20 23, arXiv : arXiv:2311.14693. doi: 10.48550/arXiv.2311.14693. [23] S. Tate, S. Fouladvand, J. H. Chen, and C. -Y. A. Chen, “The ChatGPT therapist will see you now: Navigating generative artificial intelligenc... | https://arxiv.org/abs/2505.17380v1 |
–188, Jul. 2021, doi: 10.1038/s41586 -021-03659 -0. [36] S. Rollnick and W. R. Miller, “What is Motivational Interviewing?,” Behav. Cogn. Psychother. , vol. 23, no. 4, pp. 325 –334, Oct. 1995, doi: 10.1017/S135246580001643X. [37] J. Hettema, J. Steele, and W. R. Miller, “Motivational Interviewing,” Annu. Rev. Clin. Psy... | https://arxiv.org/abs/2505.17380v1 |
A Review,” in 2021 Third International Conference on Intelligent Communication Technolo gies and Virtual Mobile Networks (ICICV) , Feb. 2021, pp. 1529 –1534. doi: 10.1109/ICICV50876.2021.9388380. [50] N. Nazareth and Y. V. Ramana Reddy, “Financial applications of machine learning: A literature review,” Expert Systems w... | https://arxiv.org/abs/2505.17380v1 |
10.48550/arXiv.2310.05189. [66] B. Oakley, A. Knafo -Noam, and M. Mcgrath, “Pathological Altruism - An Introduction,” Pathological Altruism , Dec. 2011, doi: 10.1093/acprof:oso/9780199738571.003.0014. [67] Q. X and W. B, “AI’s Role in Improving Social Connection and Oral Health for Older Adults: A Synergistic Approach,... | https://arxiv.org/abs/2505.17380v1 |
10.1371/journal.pone.0211116. [81] K. Z. Smith, P. H. Smith, J. M. Violanti, P. T. Bartone, and G. G. Homish, “Posttraumatic Stress Disorder Symptom Clusters and Perpetration of Intimate Partner Viole nce: Findings From a U.S. Nationally Representative Sample,” Journal of Traumatic Stress , vol. 28, no. 5, pp. 469–474,... | https://arxiv.org/abs/2505.17380v1 |
in AIES ’23. New York, NY, USA : Association for Computing Machinery, 2023, pp. 443 –453. doi: 10.1145/3600211.3604706. [93] Y. Tausczik and J. Pennebaker, “The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods,” Journal of Language and Social Psychology , vol. 2 9, pp. 24 –54, Mar. 2010, doi:... | https://arxiv.org/abs/2505.17380v1 |
Interview based psychotherapy,” in Proceedin gs of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference , Dec. 2012, pp. 1 –4. Accessed: Dec. 17, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/6411762 [109] K. I. Pollak et al. , “Phys ician Empathy a... | https://arxiv.org/abs/2505.17380v1 |
in Language Models,” Oct. 27, 2023, arXiv : arXiv:2310.13548. doi: 10.48550/arXiv.2310.13548. [126] N. C. Chung, G. Dyer, and L. Brocki, “Challenges of Large Language Models for Mental Health Counseling,” Nov. 23, 2023, arXiv : arXiv:2311.13857. doi: 10.48550/arXiv.2311.13857. [127] D. H. Barlow, J. T. Levitt, and L. F... | https://arxiv.org/abs/2505.17380v1 |
arXiv:2505.17387v1 [cs.CL] 23 May 2025WINGPT-3.0 T ECHNICAL REPORT WiNGPT Team∗ Winning Health AI Research Correspondence to wair@winning.com.cn ABSTRACT Current Large Language Models (LLMs) exhibit significant limitations, notably in structured, in- terpretable, and verifiable medical reasoning, alongside practical de... | https://arxiv.org/abs/2505.17387v1 |
practice. WiNGPT-3.0’s development prioritizes deep integration into hospital workflows. Clinicians, administrators, and techni- cal teams achieve this integration through a collaborative process. Together, these teams define requirements, manage system integration, and fine-tune the model using institution-specific da... | https://arxiv.org/abs/2505.17387v1 |
key techniques such as distillation, reward modelling, and chain-of-thought prompting to efficiently produce high-quality medical datasets under resource constraints. •Introduces a novel reinforcement learning approach tailored for complex clinical reasoning scenarios, including clinical diagnosis simulation and eviden... | https://arxiv.org/abs/2505.17387v1 |
Subsequently, we sampled from lowest to highest number of correct answers among the N responses. The final RL dataset consists of: 1.Verifiable dataset of 8.3K entries, primarily including types such as mathematics, medical calculations, and medical quality control; 2.Unverifiable dataset of 7K entries, mainly comprisi... | https://arxiv.org/abs/2505.17387v1 |
reliable rule-based verification of correctness. Based on this concept, we have simulated a clinical diagnostic workflow as shown in Figure 2 and constructed an evidence-based auxiliary diagnosis dataset for training clinical reasoning models. For this purpose, we selected comprehensive data from an electronic medical ... | https://arxiv.org/abs/2505.17387v1 |
data that lacks a chain of thought, we extracted healthcare data containing high-quality Long-COT annotations, using questions and answers as inputs and the chain-of-thought as outputs, forming a 20K-sample training set for the thought trajectory model based on WiNGPT-2.8. This method is particularly valuable for creat... | https://arxiv.org/abs/2505.17387v1 |
performance on clinical calculation tasks, covering 55 different types of medical calculations. •MedReMCQ contains 700 medical reasoning multiple-choice questions involving diagnostic tests, medical record quality control, and preliminary diagnosis. Examples can be found in Appendix A. •CMMLU [ 19] provides 11,582 ques... | https://arxiv.org/abs/2505.17387v1 |
with a strong base model (QwQ-32B) prior to RL fine-tuning (WiNGPT-3.0-S3-Merged) yielded substantial benefits; its superior performance across diverse benchmarks—medical (MedQA-USMLE: 87.1; MedMCQA: 71.6), general (CMMLU: 86.1), and mathematical reasoning (MATH-500: 95.6)—indicates that this integration effectively pr... | https://arxiv.org/abs/2505.17387v1 |
Luke Meyers, Vladimir Karpukhin, Brian Benedict, Mark McQuade, and Jacob Solawetz. Arcee‘s MergeKit: A toolkit for merging large language models. In Franck Dernoncourt, Daniel Preo¸ tiuc-Pietro, and Anastasia Shimorina, editors, Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Ind... | https://arxiv.org/abs/2505.17387v1 |
2025. [18] Nikhil Khandekar, Qiao Jin, Guangzhi Xiong, Soren Dunn, Serina S Applebaum, Zain Anwar, Maame Sarfo- Gyamfi, Conrad W Safranek, Abid A Anwar, Andrew Zhang, Aidan Gilson, Maxwell B Singer, Amisha Dave, Andrew Taylor, Aidong Zhang, Qingyu Chen, and Zhiyong Lu. MedCalc-Bench: Evaluating large language models fo... | https://arxiv.org/abs/2505.17387v1 |
omissions, errors, or fail to meet user needs; ,→ >Note: The "excellent answer" has undergone rigorous review and is considered to be of high standard quality, serving as a benchmark for judgment. ,→ Please output your evaluation results in the following structure: --- ### Dialogue History (in chronological order, from... | https://arxiv.org/abs/2505.17387v1 |
arXiv:2505.17390v1 [cs.CL] 23 May 2025Measuring diversity of synthetic prompts and data generated with fine-grained persona prompting Gauri Kambhatla1, Chantal Shaib2, Venkata Govindarajan3, 1The University of Texas at Austin,2Northeastern University,3Ithaca College, gkambhat@utexas.edu, shaib.c@northeastern.edu, vgovi... | https://arxiv.org/abs/2505.17390v1 |
is susceptible to caricature and stereotypying (Liu et al., 2024; Gupta et al., 2024; Wang et al., 2025; Cheng et al., 2023b,a). In this work, we examine the diversity claims pro- posed by persona-driven synthetic data pipelines. We use a suite of diversity metrics (Shaib et al., 2025) to measure the lexical diversity ... | https://arxiv.org/abs/2505.17390v1 |
synthesize plausible prompts/instructions/questions that these personas may ask. We investigate these synthesized prompts in the instruction-following (IF) domain with our suite of diversity metrics, comparing them to com- parable human-written/annotated datasets in Ta- ble 1. We chose Dolly (Conover et al., 2023) and ... | https://arxiv.org/abs/2505.17390v1 |
and in- dividual tokens. 4. SR(self-repetition) measures the tendency of LMs to repeat long n-grams across different outputs 5. Hom. BS (Homogenization score with BERTScore) uses LM embeddings to (ideally) capture “semantic” similarity. To evaluate the impact of persona-prompting and compare it against the no-persona c... | https://arxiv.org/abs/2505.17390v1 |
the cutoff condition. An explicit length cutoff in the prompt improves model diversity by reducing model self-repetition in lexical and POS patterns. Seen together with Table 5 in Appendix C, its clear that lexical diversity improves with model size, with only Deepseek-V3 ’s metrics surpassing (or matching) the human r... | https://arxiv.org/abs/2505.17390v1 |
the creative-writing subset of Dolly (which has questions/instructions that are more open-ended and thus be applicable to most personas), and present results over 100 random re-assignments of each prompt to a persona and report the mean and SD over all pairings. We leave assessments of diversity of filtered personas to... | https://arxiv.org/abs/2505.17390v1 |
Learning Representations . Kieran Healy. 2017. Fuck nuance. Sociological Theory , 35(2):118–127. Tiancheng Hu and Nigel Collier. 2024. Quantifying the persona effect in LLM simulations. In Proceedings of the 62nd Annual Meeting of the Association for Com- putational Linguistics (Volume 1: Long Papers) , pages 10289–103... | https://arxiv.org/abs/2505.17390v1 |
Shaib, Yanai Elazar, Junyi Jessy Li, and By- ron C Wallace. 2024. Detection and measurement of syntactic templates in generated text. In Proceedings of the 2024 Conference on Empirical Methods in Nat- ural Language Processing , pages 6416–6431, Miami, Florida, USA. Association for Computational Linguis- tics. Prasann S... | https://arxiv.org/abs/2505.17390v1 |
you were sent back to earth with the knowledge and ability to solve any problem on earthan academic who special- izes in the fashion and clothing of specific time periodsan academic If I had alien-bestowed omnipotence, I’d pri- oritize curing diseases, ending hunger, and halting climate col- lapse—solving root causes, ... | https://arxiv.org/abs/2505.17390v1 |
strategy and press releases for influencersa PR man- agerPalm Springs, California, offers a relaxing getaway with plenty of activities. Visitors can hike in In- dian Canyons, explore the Palm Springs Art Mu- seum, or take a hot air bal- loon ride. Golfing, shop- ping, and dining are also popular pastimes. The city’s mi... | https://arxiv.org/abs/2505.17390v1 |
nego- tiations, I remind myself that calmness is key to se- curing the best deal for my indie director clients.Breathe, darling. Prior- itize tasks, and delegate when possible. Stay fo- cused on the solution, not the problem. And remem- ber, a calm demeanor can make all the difference in high-pressure negotia- tions – ... | https://arxiv.org/abs/2505.17390v1 |
arXiv:2505.17391v1 [cs.CL] 23 May 2025Curriculum-Guided Reinforcement Learning for Efficient Multi-Hop Retrieval-Augmented Generation Yuelyu Ji University of Pittsburgh Pittsburgh, PA, USA yuj49@pitt.eduRui Meng Google Cloud AI Research Sunnyvale, CA, USA Zhuochun Li University of Pittsburgh Pittsburgh, PA, USADaqing H... | https://arxiv.org/abs/2505.17391v1 |
granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy other... | https://arxiv.org/abs/2505.17391v1 |
of prior approaches through two key innova- tions. First, we introduce a multi-objective reward mechanism that explicitly captures intermediate action quality, penalizing redun- dant queries, backtracking inefficiencies, and poor retrieval actions while simultaneously rewarding informative and novel retrieval outcomes.... | https://arxiv.org/abs/2505.17391v1 |
Multi-Hop Retrieval-Augmented Generation Conference acronym ’XX, June 03–05, 2018, Woodstock, NY Question:What retailer in ABQ Uptown is headquartered in Poole, Dorset, United Kingdom? [Current Observation] None/Retrieve Context [History] → Q1: Where is ABQ Uptown located? → Q2: Which stores are in ABQ Uptown? → Q3: Wh... | https://arxiv.org/abs/2505.17391v1 |
GPT-4 technical report outlines robust eval- uation paradigms essential for assessing large-scale model capabili- ties across diverse tasks [ 1]. Architectures inspired by the ReAct framework, which integrates reasoning and action in a unified LLM-based agent, provide interactive and adaptive retrieval agents, supporti... | https://arxiv.org/abs/2505.17391v1 |
yet allows the policy to pay the cost when it predicts that returning to a previous state will yield higher cumulative reward downstream. Refusal Reward ( 𝑟ref).In practice, unanswerable is not an oracle flag but the judgement of an external LLM verifier (ChatGPT-4o) that inspects the current evidence set 𝐷≤𝑡and ret... | https://arxiv.org/abs/2505.17391v1 |
the cumulative weighted return of trajectory 𝑥, computed using the time-dependent reward weights described in Section 3.6. A frozen LLM encoder(eg. LLaMA-3.1-8B) embeds each trajec- tory prefix, and seven parallel linear heads {𝑓(𝑘) 𝜙}7 𝑘=1(one per reward) output scalar scores. We minimize the averaged pairwise lo... | https://arxiv.org/abs/2505.17391v1 |
Action Penalty ( 𝜆) 1.5 0.8 ↘ 0.8 0.4↘ Subquery Overlap Penalty ( 𝛾) 0.1 0.5↗ 0.5 1.2↗ Backtrack Penalty ( 𝛿) 0.3 0.5 ↗ 0.5 1.0↗ Refusal Reward ( 𝜌) 0.5 0.5 – 0.5 0.5 – Step Penalty ( 𝜂) 0.02 0.05 ↗ 0.05 0.10↗ Answer Correctness ( 𝜅) 0.05 0.10 ↗ 0.10 1.00↗ Algorithm 1 EVO-RAG training loop 1: Initialise𝜋𝜃 ⊲e.g.... | https://arxiv.org/abs/2505.17391v1 |
PRM) [38] LLaMA-3.1-8B 44.1 / 56.8 50.2 / 57.9 48 / 60 51.2 / 63.1 IRCoT[30] + Flan-T5-XXL Flan-T5-XXL 45.0 / 56.2 45.4 / 56.8 19.9 / 24.9 44.0 / 55.0 EVO-RAG DeepSeek-8B 57.8 / 71.4 52.6 / 66.4 51.8 / 63.7 45.3 / 58.2 EVO-RAG LLaMA-3.1-8B 57.4 / 71.2 53.0 / 66.9 52.5 / 64.4 45.7 / 58.6 EVO-RAG Qwen-3-8B 57.6 / 71.5 53... | https://arxiv.org/abs/2505.17391v1 |
a baseline (No Reward) and a fixed two-stage scheduling (Ta- ble 4). Across all three evaluated backbones (DeepSeek-8B, LLaMA- 3.1-8B, and Qwen3-8B), the introduction of dynamic, time-based scheduling generally leads to better or comparable accuracy relative to the fixed two-stage scheduling. Notably, for DeepSeek-8B a... | https://arxiv.org/abs/2505.17391v1 |
preferable retrieval actions according to the learned preference model, indicating that search flexibility is critical for robust multi-hop retrieval. Figure 4 clearly illustrates that the full reward configuration re- duces both the median retrieval step count and variance compared to other configurations, indicating ... | https://arxiv.org/abs/2505.17391v1 |
the agent explore in the first few steps, then tightens efficiency and precision constraints as evidence accumulates. 5.2 Step-level Traces For each question we show (see Table 7) (1) the ordered sub -queries 𝑞𝑡, (2) the top retrieved passage title and a short snippet, and (3) the agent action (→A: answer or Refuse )... | https://arxiv.org/abs/2505.17391v1 |
sched- ules with adaptive or meta-learned coefficients could enable the framework to autonomously optimize reward signals across dif- ferent datasets and retrieval tasks. Transitioning from explicit dis- crete actions to latent action policies could significantly broaden EVO-RAG’s applicability to more open-ended tasks... | https://arxiv.org/abs/2505.17391v1 |
Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al .2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025). [10] Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing A Multi-hop QA Dataset for Comprehensive Evaluatio... | https://arxiv.org/abs/2505.17391v1 |
and Wei-Chang Yeh. 2022. A mixed- heuristic quantum-inspired simplified swarm optimization algorithm for sched- uling of real-time tasks in the multiprocessor system. Applied Soft Computing 131 (2022), 109807. [27] Shiqi Sun, Kun Zhang, Jingyuan Li, Min Yu, Kun Hou, Yuanzhuo Wang, and Xueqi Cheng. 2025. Retriever-gener... | https://arxiv.org/abs/2505.17391v1 |
di- verse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600 (2018). [42] Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. InInternational Conference on Learning Representations (ICLR) . ... | https://arxiv.org/abs/2505.17391v1 |
FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow Haoyu Sun Tongji UniversityHuichen Will Wang University of WashingtonJiawei Gu Sun Yat-sen UniversityLinjie Li Microsoft Yu Cheng The Chinese University of Hong Kong FullFront :Three Steps of the Full Front -End Workflow①Conceptualization 50We... | https://arxiv.org/abs/2505.17399v2 |
for image handling and layout), and interaction implementation. Our results quantitatively demonstrate performance disparities across models and tasks, and highlight a sub- stantial gap between current MLLM capabilities and human expert performance in front-end engineering. The FullFront benchmark and code are availabl... | https://arxiv.org/abs/2505.17399v2 |
inputs but often possess a narrow task scope, overlooking vital aspects such as implementing interactive features or refining existing codebases. Conversely, while WebQuest [ 3] and Webqa [ 4] investigate MLLMs’ visual understanding of webpages, the focus frequently remains on content-level reasoning, thereby neglectin... | https://arxiv.org/abs/2505.17399v2 |
generate code, particularly for complex layouts, image manipulation, and interactive functionalities, with a notable performance disparity between proprietary and open-source models. 2 Related Work Applications of MLLMs in Web Recently, the application of MLLMs in the web domain [ 5,6,7,8] has garnered considerable res... | https://arxiv.org/abs/2505.17399v2 |
elevates task complexity by presenting 75 samples, each combining 2-4 screenshots from the Real-world QA set (totaling 150 Q/A pairs), thereby challenging models to accurately identify and locate the screenshot relevant to the posed question. Questions are primarily generated by GPT-4o [ 28], augmented with bounding bo... | https://arxiv.org/abs/2505.17399v2 |
similarity of their output (rendered HTML or direct design images) against ground-truth images. This includes theCLIP Score [31], which measures high-level conceptual consistency via embedding space similarity, and the Gemini Visual Score . The latter, using Gemini 2.5 Flash, provides a fine-grained evaluation across t... | https://arxiv.org/abs/2505.17399v2 |
0.2900 0.2600 Claude 3.7 Sonnet 0.5464 0.5325 0.4533 0.5250 0.5000 0.5600 Gemini 2.5 Flash 0.4800 0.4250 0.3867 0.4550 0.4400 0.4000 GPT-4o 0.4448 0.4675 0.3733 0.4450 0.4400 0.3200 o4-mini 0.4976 0.5300 0.4400 0.4800 0.5000 0.4600 GPT-4.1 0.4672 0.4650 0.3733 0.4400 0.4200 0.3600 o1 – – – 0.4350 0.4600 0.4200 Gemini 2... | https://arxiv.org/abs/2505.17399v2 |
accuracy barely exceeding 50% across the three subtasks. Conversely, LLaV A-OneVision-72B’s accuracy remains below 35% on all QA subtasks. Critically, all models performe significantly worse than human experts, with accuracy gaps of 44.5%, 38%, and 38% on three subtasks respectively, highlighting their challenges in fi... | https://arxiv.org/abs/2505.17399v2 |
closed-source models like Claude 3.7 Sonnet and Gemini 2.5 Pro are perceived as more accurate, frequently scoring above 8/10 for reproduction quality. While these models achieve high overall fidelity, illustrative examples in Appendix D.2 reveal that even top performers can exhibit minor imperfections in fine-grained d... | https://arxiv.org/abs/2505.17399v2 |
in QA and for translating visual concepts into code might operate with different sensitivities or rely on distinct internal representations and generation strategies within MLLMs, a characteristic warranting future investigation. 5.3 Can MLLMs be an excellent front-end engineer? To determine if MLLM-generated pages are... | https://arxiv.org/abs/2505.17399v2 |
in fine-grained details, MLLMs do demonstrate the capability to design generally coherent webpage interfaces from textual descriptions and can generate correspond- ing code from webpage screenshots. However, the overall deficiencies in their perceptual abilities, coupled with the potential for critical errors during co... | https://arxiv.org/abs/2505.17399v2 |
if grounded,” arXiv preprint arXiv:2401.01614, 2024. [10] O. Yoran, S. J. Amouyal, C. Malaviya, B. Bogin, O. Press, and J. Berant, “Assistantbench: Can web agents solve realistic and time-consuming tasks?” arXiv preprint arXiv:2407.15711 , 2024. [11] K. Cheng, Q. Sun, Y . Chu, F. Xu, Y . Li, J. Zhang, and Z. Wu, “Seecl... | https://arxiv.org/abs/2505.17399v2 |
Y . Huo, W. Wang, and M. R. Lyu, “Mrweb: An exploration of gener- ating multi-page resource-aware web code from ui designs,” arXiv preprint arXiv:2412.15310 , 2024. [26] J. Xiao, Y . Wan, Y . Huo, Z. Xu, and M. R. Lyu, “Interaction2code: How far are we from automatic interactive webpage generation?” arXiv preprint arXi... | https://arxiv.org/abs/2505.17399v2 |
common real-world image content into 15 predefined categories: People, Animal, Food, Plant, Landscape, Icon, Logo, Architecture, Technology, Transportation, Map, Texture, Art, Movie, and Other (visualized in Figure 7). Each category is linked to a fixed, non-copyrighted image URL following a standardized format, such a... | https://arxiv.org/abs/2505.17399v2 |
primary HTML element involved. The ten defined interaction types, with specific implementation requirements for each, are: 1.Click to Display Dropdown ( Interaction_click_1 ):An element, when clicked, reveals a dropdown menu whose content, position, and style are contextually adapted. Requires aria-expanded attribute t... | https://arxiv.org/abs/2505.17399v2 |
reflecting the degree of similarity between the webpages. A score of 10 indicates perfect similarity (identical in every aspect), while a score of 0 indicates no similarity. For partial similarities, assign a score between 1 and 9, where higher scores reflect greater similarity. Only output a comma-separated list of 10... | https://arxiv.org/abs/2505.17399v2 |
gutters) both within and between elements, compared to the ground-truth design. •Score 10: All elements exhibit perfect alignment and spacing as per the original design. •Score 6-8: Minor, subtle misalignments or inconsistent spacing that do not significantly impact readability or aesthetics. •Score 1-5: Noticeable and... | https://arxiv.org/abs/2505.17399v2 |
text styling attributes. •Score 0: Text styles are completely different. 9.Text Content Accuracy (Score: 0-10): This evaluates if the primary textual content (headings, body text, labels, captions) displayed on the generated webpage accurately reproduces the text from the original design, without omissions, additions, ... | https://arxiv.org/abs/2505.17399v2 |
( Rate c) is calculated. This reflects the proportion of reference elements found and successfully matched in the generated HTML: Rate c=|Mc| |Eref,c|(2) If|Eref,c|is zero, Rate cis 1.0. The code tracks text_implementation_rate , image_implementation_rate , and form_implementation_rate . Similarity Scores for Matched E... | https://arxiv.org/abs/2505.17399v2 |
the Webpage Design task. The Webpage Design task evaluates an MLLM’s ability to generate a visual webpage design based on a textual description, assessing its capacity for conceptualization within the front-end workflow. Figure 8 illustrates the outputs from two evaluated text-to-image MLLMs, GPT-4o and gemini-2.0-flas... | https://arxiv.org/abs/2505.17399v2 |
regarding the tag’s position relative to the title, all these MLLMs correctly implement the “Human Rights Advocate” tag above the main “NA VI PILLAY” title in their generated code. text with center alignment, deviating from the original left alignment. Furthermore, none of the evaluated models successfully replicated t... | https://arxiv.org/abs/2505.17399v2 |
arXiv:2505.17407v1 [cs.CL] 23 May 2025 2025-5-26 Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? Zhi Rui Tam1, Cheng-Kuang Wu1, Yu Ying Chiu2, Chieh-Yen Lin1, Yun-Nung Chen3 and Hung-yi Lee3 1Appier AI Research,2University of Washington,3National Taiwan University Large re... | https://arxiv.org/abs/2505.17407v1 |
[ 8], programming [ 11], and PhD-level science questions [ 15]. Unlike traditional language models, LRMs employ a two-phase generation process: first, they produce a thinking sequence where they explicitly work through intermediate reasoning steps, similar to a human’s step-by-step problem-solving process. This thinkin... | https://arxiv.org/abs/2505.17407v1 |
deployment. 2. We introduce a novel segmentation-classification method for analyzing reasoning patterns in LRMs. Using this approach, we identify systematic correlations between language-specific prefill tokens and reasoning strategies: Chinese significantly promotes subgoal setting (Pearson’s r = 0.51), while English ... | https://arxiv.org/abs/2505.17407v1 |
these models predominantly default to a small subset of languages—primarily English and Chinese—regardless of the input language. We term these dominant languages “reasoning hubs” as they appear to function as central linguistic nodes for multilingual reasoning processes. As illustrated in Figure 2, our language detect... | https://arxiv.org/abs/2505.17407v1 |
te zh-CN id Detected Language100.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 48.8 51.2 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 24.2 0.0 0.0 0.0 0.0 75.8 0.0 12.9 0.0 0.0 4.7 0.0 0.0 0.0 82.3 0.0 28.7 0.0 0.0 0.0 58.9 0.0 0.0 12.4 0.0 84.2 0.0 0.0 0.0 0.0 13.4 0.0 0.0 2.5 90.6 0.0 0.0 0.0 0.0 0.0 2.4 7.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0... | https://arxiv.org/abs/2505.17407v1 |
kk Detected Languageenesja koru swte zh-CNInput Language100.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 100.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 100.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 100.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 100.0 0.0 0.0 0.0 0.0 28.4 0.0 0.0 0.0 0.0 71.6 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 100.0 0.0 0.... | https://arxiv.org/abs/2505.17407v1 |
Target) -1.4% +22.2% +0.2% +37.8% +21.6% +31.8% +0.6% QwQ-32B Prefill English (EN) 92.4% 92.2% 91.2% 67.8% 90.2% 84.4% 90.6% Prefill Target Language 90.6% 93.2% 90.6% 55.6% 87.4% 65.2% 88.2% Difference (EN - Target) +1.8% -1.0% +0.6% +12.2% +2.8% +19.2% +2.4% Qwen3-30B-A3B Prefill English (EN) 91.4% 91.0% 90.6% 72.4% 8... | https://arxiv.org/abs/2505.17407v1 |
percentage points for Japanese, Korean, Chinese, and Spanish inputs. Interestingly, the Russian language exhibits the opposite pattern, with lower toxicity when reasoning is guided toward English rather than maintaining native Russian reasoning. This asymmetric effect aligns with our broader findings about reasoning hu... | https://arxiv.org/abs/2505.17407v1 |
pipeline for step-level category annotation of reasoning chains. 5.1. Segmentation-Classification Method Segmentation The first stage of our methodology involves segmenting reasoning chains into distinct operational steps with clear boundaries. This segmentation is crucial for preventing overcounting and ensuring that ... | https://arxiv.org/abs/2505.17407v1 |
the four reasoning habits. Subsequently, for each prefill target language (e.g., Chinese, Swahili) and each reasoning habit (e.g., Subgoal setting), we calculate the pearson correlations between the average counts per reasoning and the final accuracy. Figure 5 demonstrates that these minimal linguistic cues fundamental... | https://arxiv.org/abs/2505.17407v1 |
high success. We demonstratedanasymmetriceffect:forcingmodelstoreasoninnon-hublanguagesdegradesperformance in low-resource languages, whereas aligning reasoning with hub languages improves or maintains the 11 performance in reasoning tasks. However, in the cultural reasoning task, native-language reasoning can be benef... | https://arxiv.org/abs/2505.17407v1 |
Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori Hashimoto. s1: Simple test-time scaling. arXiv preprint arXiv:2501.19393 , 2025. [13]Gustaw Opiełka, Hannes Rosenbusch, and Claire E Stevenson. Analogical reasoning inside large language models: Con... | https://arxiv.org/abs/2505.17407v1 |
experiments including ablation studies in scaling efficiency. Whileothermodels:Deepseek-Distill-Qwen-14B,Deepseek-Distill-Llama-8B,Qwen3-30B-A3Bcostaround 1,200 USD in A100 GPUs cost calculated at 1.8 USD per hour per card. The entire inference process took over 2 weeks to finish under 2 A100 GPUs, using the latest sgl... | https://arxiv.org/abs/2505.17407v1 |
Now do the same task by following the same pattern as above: [INPUT]: “‘ thinking process goes here “‘ [OUTPUT]: Figure 8 ∣The prompt template for segmenting reasoning steps with <sep> tokens. 18 B.2. Reasoning Process Classification After segmentation, we concatenate the individual reasoning processes using numbered s... | https://arxiv.org/abs/2505.17407v1 |
C. Limiting Tokens to Control Output Language We explore the idea of limiting the available allowed tokens during decoding to force LRM to output in a certain language. This solution would allows more freedom of what kind of reasoning compare to our method which seeds the initial reasoning with a opening phrase. We fir... | https://arxiv.org/abs/2505.17407v1 |
Хорошо 278 Хорошо (386) Qwen-14B zh-CN 首先 ， 181 首先(181) QwQ-32B es Okay, 489 Primero (3) QwQ-32B sw Okay, 474 Ili kup (2) QwQ-32B en Okay, 477 Okay, (477) QwQ-32B ja Alright, 208 まず(123) QwQ-32B ko 좋ᄋ ᅡ 220좋ᄋ ᅡ(220) QwQ-32B ru Хорошо 365 Хорошо (365) QwQ-32B zh-CN 嗯 ， 479 嗯 ，(479) QwQ-32B te Okay, 499 pr ¯arambhim ... | https://arxiv.org/abs/2505.17407v1 |
73.4% Difference (EN - Native) – +1.4% -0.1% +8.1% +5.9% +7.7% QwQ-32B Prefill English – 88.7% 89.1% 59.8% 87.8% 85.8% Prefill target Language 91.4% 88.5% 89.2% 23.8% 88.3% 83.6% Difference (EN - Native) – +0.3% -0.1% +36.0% -0.5% +2.2% Qwen3-30B-A3B Prefill English – 88.9% 89.0% 61.1% 86.8% 82.1% Prefill target Langua... | https://arxiv.org/abs/2505.17407v1 |
english reasoning in QwQ-32B 31 Table 14 ∣AIME-24 pass@8 from Qwen3-30B-A3B basemodel with different initial phrase for text completion. Language en zh-CN ja ru ko sw Phrase Okay 嗯まずХорошо 먼저Kwa kuzingatia pass@8 0.267 0.190 0.172 0.133 0.133 0.200 H. Study of Impact of Prefill Tokens in Pretrained Model To investigate... | https://arxiv.org/abs/2505.17407v1 |
Backward Subgoal Setting Verification English -0.07 0.34∗∗0.22 0.07 Spanish 0.08 -0.16 −0.27∗−0.26∗ Japanese 0.16 -0.19 -0.19 −0.29∗ Korean -0.03 0.12 0.02 0.05 Russian -0.06 0.02 0.09 0.05 Swahili -0.22 −0.25∗−0.35∗∗0.16 Telugu -0.01 -0.18 -0.12 -0.20 zh-CN 0.23∗0.02 0.50∗∗∗0.41∗∗∗ ∗𝑝<0.05,∗∗𝑝<0.01,∗∗∗𝑝<0.001 Table... | https://arxiv.org/abs/2505.17407v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.