text string | source string |
|---|---|
the total number of ideas tested (format: improved / successful / tested). MethodAutoRYP Auto2DCls AutoSenCls Max R2Avg R2Ideas (i/s/t) Max Acc Avg Acc Ideas (i/s/t) Max Acc Avg Acc Ideas (i/s/t) Baseline 27.6 27.6 - 81.2 81.2 - 91.0 91.0 - NOVEL SEEK (w/o AE) 34.7 33.0 2/5/10 81.6 81.5 2/5/10 92.4 91.9 6/8/10 NOVEL SE... | https://arxiv.org/abs/2505.16938v2 |
we conduct 10 ex- periments. AI-Scientist-V2 and AI-Researcher demonstrate relatively weak baseline im- provement capabilities, with AI-Scientist-V2 in particular struggling to write code that runs correctly. The primary reason lies in the fact that AI-Scientist-V2’s pipeline utilizes limited task-related information (... | https://arxiv.org/abs/2505.16938v2 |
tasks, whereas AI-Researcher is unable to improve the provided baselines. One important reason for NOVEL SEEK’s outstanding performance is its ability to generate novel ideas through extensive search and reflection. Moreover, NOVEL SEEK has a complete experimental planning and adaptive evolution mech- anism, thereby en... | https://arxiv.org/abs/2505.16938v2 |
this system not only combines 1D and 2D molecular representations effectively but also improves prediction accuracy and model adaptability. Consequently, this showcase underscores the method’s potential for advancing research in complex chemical tasks using deep learning. In the AutoMD task illustrated in Fig. 6, a nov... | https://arxiv.org/abs/2505.16938v2 |
20 ideas. The detailed scores for each idea can be found in the Appendix B.1. Research Task Idea-gen Method Soundness Contribution Overall Confidence Reaction Yield Prediction AI-Scientist-V2 1.42 1.45 3.50 3.50 Reaction Yield Prediction NOVEL SEEK 3.09 2.66 4.35 4.00 2D Semantic Segmentation AI-Scientist-V2 1.84 2.07 ... | https://arxiv.org/abs/2505.16938v2 |
discovery by enabling LLM agent labo- ratories to communicate and build upon each other’s work via a shared preprint server, thus 21 NovelSeek: Starting Point of Innovation facilitating knowledge sharing and collective innovation. Experimental results demonstrate that agent laboratories utilizing AgentRxiv for collabor... | https://arxiv.org/abs/2505.16938v2 |
train and improve themselves. This mechanism should focus on improving their ability to gather feedback from three key sources: the environment, interactions with other agents, and human experts. •Scientific Discovery-related Benchmark Construction: This involves evaluating the value that an idea can bring, rather than... | https://arxiv.org/abs/2505.16938v2 |
Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xinxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, et al. Chain of ideas: Revolutionizing research in novel idea development with llm agents. arXiv preprint arXiv:2410.13185 , 2024b. Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, ... | https://arxiv.org/abs/2505.16938v2 |
Point of Innovation OpenPCDet Development Team. Openpcdet: An open-source toolbox for 3d object detection from point clouds. https://github.com/open-mmlab/OpenPCDet , 2020. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, et al. Qwen2-vl: Enhancing vi... | https://arxiv.org/abs/2505.16938v2 |
Zhang, and Qiang Xu. Are transformers effective for time series forecasting? In Proceedings of the AAAI conference on artificial intelligence , volume 37, pp. 11121–11128, 2023. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. Sigmoid loss for language image pre-training. In Proceedings of the IEEE/C... | https://arxiv.org/abs/2505.16938v2 |
and NOVEL SEEK, and five experienced researchers were invited to score each idea. In this part, we provide a detailed description of the scoring criteria for each reviewer, as outlined below: Soundness : • 4 excellent 27 NovelSeek: Starting Point of Innovation • 3 good • 2 fair • 1 poor Contribution : • 4 excellent • 3... | https://arxiv.org/abs/2505.16938v2 |
not carefully checked. B.2 Information on the Expert Review Process Qualifications for Human Evaluators : Evaluators must hold a Ph.D. or be Ph.D. candidates with reviewing experience in top-tier AI conferences such as ICLR, ICML, NeurIPS, CVPR, ICCV , and ACL. Steps for Expert Evaluation and Validation : •Before the e... | https://arxiv.org/abs/2505.16938v2 |
regularization Add feature-wise attention mechanism Optimize perturbation embedding alignment Performance Reflection 0.047 MSE improvement Multi-scale regularization and enhanced attention further improve performance Evolutionary Planning Implement hierarchical regularization Add adaptive lr for different components In... | https://arxiv.org/abs/2505.16938v2 |
adaptation, andattentionmechanisms,aimedatimprovingcomputationalefficiencyandfeaturerobustness.Thehierarchicalgraphconstructionexplicitlymodelslocal-to-globalrelationshipsinadensity-adaptivemannerwhiletheself-attentionmechanismisredefinedtoalignpoint-levelandgraph-levelfeatureseffectively.Code ###FullAlgorithm1.**Densi... | https://arxiv.org/abs/2505.16938v2 |
arXiv:2505.16944v1 [cs.AI] 22 May 2025AGENT IF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios Yunjia Qi1∗, Hao Peng1∗, Xiaozhi Wang1, Amy Xin1, Youfeng Liu2, Bin Xu1,Lei Hou1,Juanzi Li1 1Tsinghua University2Zhipu AI {qyj23, peng-h24}@mails.tsinghua.edu.cn Abstract Large Language Model... | https://arxiv.org/abs/2505.16944v1 |
from real-world agentic applications. Figure 2 illustrates an instruction from a real-world agentic scenario. We can observe that the instruction is long with complex structures and constraint types, such as condition constraints, example constraints, and tool specifications, posing novel and significant challenges for... | https://arxiv.org/abs/2505.16944v1 |
in days', 'type': 'int', 'required': 'False’}}Example: Refer to the following example to solve the problem. Note that your response should follow the same format:input:<task>I will use the search function to query "Beijing today temperature" to get today's temperature information for Beijing.</task>output:<code>'''1. U... | https://arxiv.org/abs/2505.16944v1 |
which presents significant challenges to current LLMs. 3 A GENT IF This section presents a detailed introduction to AGENT IF, including 4 parts: the constraint taxonomy (§ 3.1), the dataset construction process (§ 3.2), the statistics of AGENT IF(§ 3.3), and the evaluation protocol (§ 3.4). Figure 3 illustrates the dat... | https://arxiv.org/abs/2505.16944v1 |
model to infer and follow constraints from given output examples, which requires analogical reasoning and inductive capabilities. 3.2 Dataset Construction As shown in Figure 3, AGENT IFis constructed through a semi-automated pipeline consisting of three main steps: agentic instruction collection, constraint extraction,... | https://arxiv.org/abs/2505.16944v1 |
constraint to verify its completeness and consistency with the original instruction. As a result, we obtain 8,415high-quality constraints in total, with an average of 11.9constraints per instruction. Evaluation Generation Finally, we annotate each constraint with its corresponding evaluation method. Following prior wor... | https://arxiv.org/abs/2505.16944v1 |
proprietary and open-source LLMs on AGENT IF, sorted by CSR in descending order. [N] denotes non-thinking models, [T] denotes thinking models, and [S] denotes models explicitly designed for instruction following by the academic community. As described in § 3.4, CSR indicates the proportion of correctly followed individ... | https://arxiv.org/abs/2505.16944v1 |
challenge to existing LLMs, highlighting the need for further research in instruction following under real-world agentic scenarios. As instruction following is a prerequisite ability for building reliable LLM-based agents, we argue that prior to developing agents, it is crucial to evaluate the fundamental instruction-f... | https://arxiv.org/abs/2505.16944v1 |
Specifically, we select all the failed conditional constraints from each investigated model, remove their conditional components, and then convert them into vanilla constraints that must be met while keeping all other elements unchanged. If the model then succeeds, it indicates an error in condition checking; if it sti... | https://arxiv.org/abs/2505.16944v1 |
by instruction length or number of constraints, then compute the success rates within each bucket. The results are shown in Figure 5. We observe that model performance generally declines with increasing instruction length or constraint count, indicating that longer instructions or those with 8 Meta ConstraintConstraint... | https://arxiv.org/abs/2505.16944v1 |
a diverse range such as condition and tool constraints. We evaluate various representative and advanced LLMs onAGENT IFand find that current models generally perform poorly, and the best model perfectly follows fewer than 30% of the instructions, which suggests that AGENT IFposes a significant challenge. We further con... | https://arxiv.org/abs/2505.16944v1 |
Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. Mistral 7b, 2023. [14] Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, ... | https://arxiv.org/abs/2505.16944v1 |
Lindong Wu, Hao Huang, Jinfeng Zhou, Wenchuang Li, Binxin Hu, Wendy Gao, Jiaxing Xu, et al. Benchmarking complex instruction-following with multiple constraints composition. Advances in Neural Information Processing Systems , 37:137610– 137645, 2024. [30] Kaiwen Yan, Hongcheng Guo, Xuanqing Shi, Jingyi Xu, Yaonan Gu, a... | https://arxiv.org/abs/2505.16944v1 |
and service requests and do not conduct user behavior analysis. Notably, the agents include only system prompts without any user queries to prevent information leakage. Instead, all user queries in AGENT IFare created by hired annotators. AGENT IFwill be released under the GPL-3.0 license. (2) Broader Impacts. This wor... | https://arxiv.org/abs/2505.16944v1 |
instruc- tion. We categorize this type into three distinct forms: Vanilla Constraints are stated directly and uncon- ditionally in the prompt. These constraints are always in effect, regardless of the input content or model be- havior. For example, “Answer in Chinese”, i.e., the model must always respond in Chinese, re... | https://arxiv.org/abs/2505.16944v1 |
Experimental Hyperparameters. In all experiments, we set the temperature to 0to ensure repro- ducibility. The maximum number of generated tokens is set to 32,000. For models with a context length shorter than 32,000tokens, we set their maximum allowable context length to match the max-token limit. Experiment Cost. We u... | https://arxiv.org/abs/2505.16944v1 |
more of the following categories. Prefer to choose only one category unless you believe the constraint clearly fits multiple types . After classification, provide a brief explanation supporting your decision. Constraint Categories: 1.formatting —Controls the structure or presentation format of the output. Examples incl... | https://arxiv.org/abs/2505.16944v1 |
Directly by code 2.llm_assisted_code — By code after extracting needed content via LLM 3.llm — Only by using LLM to semantically assess it Please follow these guidelines: •If the constraint can be validated by simple logic (e.g., length, presence, format) and the content is directly accessible from the response, classi... | https://arxiv.org/abs/2505.16944v1 |
dictionary in the following format: { "extraction_instruction": "{your generated extraction instruction}. Return the extracted content verbatim from the response. If multiple segments are found, return them as a Python-style list of strings. If nothing is found, return None." } Input: Instruction Paragraph: Here is the... | https://arxiv.org/abs/2505.16944v1 |
on the scope of the claims made, e.g., if the approach was only tested on a few datasets or with a few runs. In general, empirical results often depend on implicit assumptions, which should be articulated. •The authors should reflect on the factors that influence the performance of the approach. For example, a facial r... | https://arxiv.org/abs/2505.16944v1 |
a specific model and empirical evaluation, it may be necessary to either make it possible for others to replicate the model with the same dataset, or provide access to the model. In general. releasing code and data is often one good way to accomplish this, but reproducibility can also be provided via detailed instructi... | https://arxiv.org/abs/2505.16944v1 |
data and code is permitted. 6.Experimental setting/details Question: Does the paper specify all the training and test details (e.g., data splits, hyper- parameters, how they were chosen, type of optimizer, etc.) necessary to understand the results? Answer: [Yes] Justification: In Appendix E. Guidelines: • The answer NA... | https://arxiv.org/abs/2505.16944v1 |
every respect, with the NeurIPS Code of Ethics https://neurips.cc/public/EthicsGuidelines ? Answer: [Yes] Justification: In Appendix B. Guidelines: •The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics. •If the authors answer No, they should explain the special circumstances that require a ... | https://arxiv.org/abs/2505.16944v1 |
and make a best faith effort. 12.Licenses for existing assets Question: Are the creators or original owners of assets (e.g., code, data, models), used in the paper, properly credited and are the license and terms of use explicitly mentioned and properly respected? Answer: [Yes] Justification: In Appendix B. Guidelines:... | https://arxiv.org/abs/2505.16944v1 |
does not involve crowdsourcing nor research with human subjects. •Depending on the country in which research is conducted, IRB approval (or equivalent) may be required for any human subjects research. If you obtained IRB approval, you should clearly state this in the paper. •We recognize that the procedures for this ma... | https://arxiv.org/abs/2505.16944v1 |
On Multilingual Encoder Language Model Compression for Low-Resource Languages Daniil Gurgurov1,2Michal Gregor3Josef van Genabith1,2Simon Ostermann1,2,4 1Saarland University 2German Research Center for Artificial Intelligence (DFKI) 3Kempelen Institute of Intelligent Technologies (KInIT) 4Centre for European Research in... | https://arxiv.org/abs/2505.16956v1 |
friendly models (Strubell et al., 2020) for low- resource languages and explores how strongly mod- els can be compressed. 2 Methodology In this section, we present our multilingual model compression strategy, illustrated in Figure 1. Our approach combines several existing compression techniques in a novel way that, to ... | https://arxiv.org/abs/2505.16956v1 |
Bottleneck task adapters (Pfeiffer et al., 2020) with fixed hyperparameters (see Appendix H). Per- formance is measured using macro-averaged F1 (Sokolova et al., 2006) for TC and SA, and "seqe- val" F1 (Nakayama, 2018) for NER and POS. 3.3 Models and Baselines We compress two encoder-only multilingual models–mBERT (Dev... | https://arxiv.org/abs/2505.16956v1 |
not prune attention heads, as removing even a minimal number (e.g., three) causes severe degradation. Hidden size reduction: We reduce the hidden embedding size to 564, 456, and 312,1truncat- ing it to the first kdimensions. Training is per- formed under the supervision of the student from the previous stage. We find t... | https://arxiv.org/abs/2505.16956v1 |
largest fine-tuning dataset—remains robust even under the maximum compression, indicating that a stronger teacher model facilitates better compres- sion outcomes. Swahili, with a moderate dataset size, follows an intermediate pattern. The results support a relationship between fine-tuning data vol- ume and the model’s ... | https://arxiv.org/abs/2505.16956v1 |
of mutililingual BERT. In Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing , pages 119–123, Online. Association for Computational Linguistics. David Ifeoluwa Adelani, Hannah Liu, Xiaoyu Shen, Nikita Vassilyev, Jesujoba O. Alabi, Yanke Mao, Hao- nan Gao, and En-Shiun Annie Lee. 2024... | https://arxiv.org/abs/2505.16956v1 |
Agbolo, Sey- dou Traore, Chinedu Uchechukwu, Aliyu Yusuf, Muhammad Abdullahi, and Dietrich Klakow. 2023. MasakhaPOS: Part-of-speech tagging for typolog- ically diverse African languages. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages 10883–1090... | https://arxiv.org/abs/2505.16956v1 |
Al- ham Fikri Aji. 2022. Which student is best? a comprehensive knowledge distillation exam for task- specific bert models. Xiaoman Pan, Boliang Zhang, Jonathan May, Joel Noth- man, Kevin Knight, and Heng Ji. 2017. Cross-lingual name tagging and linking for 282 languages. In Pro- ceedings of the 55th Annual Meeting of ... | https://arxiv.org/abs/2505.16956v1 |
Akbarianto Wibowo, Thamar Solorio, and Al- ham Fikri Aji. 2024. The privileged students: On the value of initialization in multilingual knowledge distillation.A KL Divergence vs MSE for Knowledge Distillation (a) Maltese (b) Slovak (c) Swahili Figure 3: MSE vs. KD validation accuracy for mBERT with the models initializ... | https://arxiv.org/abs/2505.16956v1 |
1e-4 3e-4 3e-4 Batch size 16 16 64 64 Epochs 20 20 100 100 Maximum length 256 256 512 512 Table 4: Hyperparameters for task adapter fine-tuning across Text Classification (TC), Sentiment Analysis (SA), and Named Entity Recognition (NER) tasks. I Adapter Trainable Parameter Counts To examine whether the constrained task... | https://arxiv.org/abs/2505.16956v1 |
MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning Suhao Yu1∗Haojin Wang2∗Juncheng Wu3∗Cihang Xie3Yuyin Zhou3 1University of Pennsylvania2University of Illinois Urbana-Champaign3UC Santa Cruz Project Page :https://ucsc-vlaa.github.io/MedFrameQA/ Benchmark :https://huggingface.co/datasets/SuhaoYu1020... | https://arxiv.org/abs/2505.16964v1 |
Lower Left Is the lung healthy? Answer : No MedXpertQAMedFrameQA (Ours) Q : A 39-year-old man presents with a history of an index finger injury sustained 6 months ago that has not improved despite eight weeks of splinting. Radiographs from the time of injury (Figure A) and a recent follow-up (Figure B) are provided. Wh... | https://arxiv.org/abs/2505.16964v1 |
accessible platform for medical education [ 19,20,21]— which provides a rich repository of medical and clinical videos with temporally and semantically connected visual content. Building on this insight and drawing inspiration from the prior work [ 22], we propose a VQA generation pipeline that automatically constructs... | https://arxiv.org/abs/2505.16964v1 |
QAand find that their accuracies mostly fall below 50% with substantial performance across different body systems, organs, and modalities, highlighting the substantial gap between current model capabilities and real-world diagnostic requirements. 2 Related Work Reasoning Multimodal Large Language Models With advances i... | https://arxiv.org/abs/2505.16964v1 |
instructional and nursing procedures. A VOS [ 36] includes 1,997 annotated open-surgery videos across 23 procedures and 50 countries. MIMIC-IV-ECHO [ 37] provides echocardiography videos for cardiac imaging research. Cotaract-1K [ 38] consists of 1,000 videos of cataract surgeries conducted in the eye clinic from 2021 ... | https://arxiv.org/abs/2505.16964v1 |
the same time interval. However, narration in medical videos can lag behind or precede the exact moment a frame is shown. To associate each frame ( Fi) with all relevant speech, we define a symmetric margin ( ∆) seconds around the frame’s interval and gather every transcript whose span intersects that window fi start−... | https://arxiv.org/abs/2505.16964v1 |
Appendix E.3. Lastly, each clip is packaged as {Q, A, R, [Fi, Fi+1···]}, forming a single entry. 3.5 Data Filtering Difficulty Filtering. To ensure the high challenge of MEDFRAME QA, we utilize 3 advanced MLLMs—GPT-4-Turbo-V [ 28],o1[40], and GPT-4o [39]—for further filtering. If anyof the models selects the correct op... | https://arxiv.org/abs/2505.16964v1 |
are highlighted in bold. In general, all assessed models demonstrate persistently low accuracy, with system-wise performance of substantial variability in task difficulty. ModelAccuracy per SystemAvg CNS RES CIR DIG URI REP END MSK AUX Proprietary Reasoning Models o1 46.91 48.88 49.49 47.45 49.03 42.26 47.68 51.59 48.7... | https://arxiv.org/abs/2505.16964v1 |
displacement of the nerve root, despite clear imaging evidence of lateral displacement caused by a foraminal disc herniation. This initial misjudgment propagates through its reasoning chain, ultimately resulting in the selection of an anatomically incorrect answer that contradicts the information integrated across both... | https://arxiv.org/abs/2505.16964v1 |
report the accuracy of models on questions in MEDFRAME QAgrouped by frame count with standard deviation ( SD) and by modality. We empirically observe that accuracy fluctuates with increasing frame count and varies significantly across common imaging modalities. ModelAccuracy (%) by Frame Count Accuracy (%) by Modality ... | https://arxiv.org/abs/2505.16964v1 |
foramen laterally, pushing the exiting (right ‐ sided) nerve root inward (medially) and obliterating the usual bright (fat) rim around the root on T1. This corresponds to a foraminal herniation displacing the nerve root medially and eliminating its surrounding fat. Answer: A The first image shows a mass compressing the... | https://arxiv.org/abs/2505.16964v1 |
thank the Microsoft Accelerate Foundation Models Research Program for supporting our comput- ing needs. 9 References [1]Yunfei Xie, Ce Zhou, Lang Gao, Juncheng Wu, Xianhang Li, Hong-Yu Zhou, Sheng Liu, Lei Xing, James Zou, Cihang Xie, and Yuyin Zhou. Medtrinity-25m: A large-scale multimodal dataset with multigranular a... | https://arxiv.org/abs/2505.16964v1 |
A. Hasan, Vivek V . Datla, Joey Liu, Dina Demner-Fushman, and Henning Müller. Vqa-med: Overview of the medical visual question answering task at imageclef 2019. In Working Notes of CLEF 2019 , volume 2380 of CEUR Workshop Proceedings , Lugano, Switzerland, September 9-12 2019. CEUR-WS.org. URL https: //ceur-ws.org/Vol-... | https://arxiv.org/abs/2505.16964v1 |
Kaiyan Zhang, Ning Ding, and Bowen Zhou. Medxpertqa: Benchmarking expert-level medical reasoning and understanding. CoRR , abs/2501.18362, 2025. doi: 10.48550/ARXIV .2501.18362. URL https://doi.org/10.48550/arXiv.2501.18362 . [19] Wafa Osman, Faiza Mohamed, Mohamed Elhassan, and Abdelilah Shoufan. Is youtube a reliable... | https://arxiv.org/abs/2505.16964v1 |
via large-scale weak supervision. In Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett, editors, International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA , volume 202 of Proceedings of Machine Learning Research , pages 28492–285... | https://arxiv.org/abs/2505.16964v1 |
Paino, Alex Renzin, Alex Tachard Passos, Alexander Kirillov, Alexi Christakis, Alexis Conneau, Ali Kamali, Allan Jabri, Allison Moyer, Allison Tam, Amadou Crookes, Amin Tootoonchian, Ananya Kumar, Andrea Vallone, Andrej Karpathy, Andrew Braunstein, An- drew Cann, Andrew Codispoti, Andrew Galu, Andrew Kondrich, Andrew T... | https://arxiv.org/abs/2505.16964v1 |
technical report. CoRR , abs/2502.13923, 2025. doi: 10.48550/ARXIV .2502.13923. URL https://doi.org/10.48550/arXiv.2502.13923 . [46] Qianqi Yan, Xuehai He, Xiang Yue, and Xin Eric Wang. Worse than random? an embarrass- ingly simple probing evaluation of large multimodal models in medical vqa. arXiv preprint arXiv:2405.... | https://arxiv.org/abs/2505.16964v1 |
stones CT urethra urethral stricture urethrography urethral injury CT urethrography reproductive system testes testicular cancer ultrasound testicular torsion Doppler ultrasound epididymitis ultrasound prostate prostate cancer MRI benign prostatic hyperplasia TRUS prostatitis pelvic CT 1 16 System Organ Keyword penis e... | https://arxiv.org/abs/2505.16964v1 |
47.31 58.06 40.86 aorta 60.81 48.65 45.21 50.00 45.83 35.14 35.14 41.89 43.24 32.43 heart 55.88 52.94 51.52 51.52 53.12 26.47 35.29 32.35 47.06 41.18 digestive system large intestine 47.29 47.29 42.64 38.28 41.73 48.06 23.26 46.51 33.59 30.47 esophagus 59.26 51.85 70.37 62.96 59.26 62.96 22.22 62.96 59.26 48.15 small i... | https://arxiv.org/abs/2505.16964v1 |
time in seconds - `"sentence"`: caption content ### Your Task 1. **Determine Benchmark Eligibility**: Answer these questions to guide your reasoning : 1. Does the image prominently depict clear , authentic medical imaging relevant to "{keyword}" (e.g., sharp radiographs or scans, including multiple images if they are a... | https://arxiv.org/abs/2505.16964v1 |
segments: ``` {caption} ``` Requir ements: - Focus only on medically or visually coherent topics. - Do not group captions based only on linguistic similarity—there must be a medically meaningful connection. - Each group must contain at least one caption. - If a caption clearly describes a dif ferent topic from others, ... | https://arxiv.org/abs/2505.16964v1 |
’ Answer: $LETTER ’ (without quotes) where LETTER is one of the options. For example, if the correct answer is A, your response should be: ’Answer: A’. Think step by step before answering. Question:{question} Options: {options} Gemini Pr ompt Template: Answer the following multiple-choice question. Images are provided.... | https://arxiv.org/abs/2505.16964v1 |
nervous system Organ : brain Modality : CT YouTube Link : https://youtu.be/ eoxKSAoGW2s Options: A. Acute ischemic stroke involving the right anterior cerebral artery and middle cerebral artery territories with significant mass ef fect and early signs of herniation. B. Chronic ischemic changes in the right cerebral hem... | https://arxiv.org/abs/2505.16964v1 |
Whitening of the end plates due to prolonged stress is mentioned in image_3 and image_4, further supporting degeneration. The vacuum phenomenon, described in image_3 and image_4, is a key feature of advanced degeneration, where gas accumulates in the disc space due to fluid loss. These findings collectively point to ad... | https://arxiv.org/abs/2505.16964v1 |
BP-Seg : A graphical model approach to unsupervised and non-contiguous text segmentation using belief propagation Fengyi Li, Kayhan Behdin, Natesh Pillai, Xiaofeng Wang, Zhipeng Wang, Ercan Yildiz LinkedIn Corporation {fenli, kbehdin, napillai, xiaofwan, zhipwang, eyildiz}@linkedin.com Abstract Text segmentation based ... | https://arxiv.org/abs/2505.16965v1 |
typically more related, while also enabling the grouping of non-contiguous sen- tences that are semantically similar. To achieve this, we first embed sentences into vector represen- tations using sentence embeddings (Reimers and Gurevych, 2019), so that semantically similar sen- tences are mapped closer together in the... | https://arxiv.org/abs/2505.16965v1 |
ψi,j(xi, xj) =( 1, x i=xj exp(−ϕi,j) otherwise ,(2) where ϕi,j=λ 2(−sim(Ri, Rj) + 1) exp( −|i−j|2/σ). (3) Here, sim(·,·)denotes the cosine similarity be- tween two embeddings. A higher value of ψi(xi) indicates a greater likelihood that sentence Sibe- longs to segment xi. Note also that ψi,j(xi, xj)≤ 1, with equality h... | https://arxiv.org/abs/2505.16965v1 |
covers segmentations by finding maximal cliques — fundamentally different from our probabilistic strategy, in which we seek an assignment that max- imizes the marginal distribution. One could in prin- ciple apply k-means to group sentence embeddings;Algorithm 1 BP-Seg 1:Input: Sentence embeddings {R1, . . . , R n} 2:Ou... | https://arxiv.org/abs/2505.16965v1 |
fully group the tennis-related sentences in the same cluster in 5out of the 6tested values of k. For GraphSeg , we set the minimum number of sen- tences per segment to 1 to allow maximum flexibil- ity. However, despite trying various thresholds τ, GraphSeg fails to cluster thematically related sen- tences effectively, ... | https://arxiv.org/abs/2505.16965v1 |
examples may not accurately reflect real-world scenarios, and our evaluations are lim- ited to these two cases. Nevertheless, we believe the insights from our findings will inspire further research in text segementation and benefit a wide range of related applications. Ethics Statement In this paper, we utilize data fr... | https://arxiv.org/abs/2505.16965v1 |
critique and improvement of an evaluation metric for text segmentation. Computational Linguistics , 28(1):19– 36. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. pages 3973–3983. Shiwon Song. 2021. The informational value of seg- ment data disaggregated by underlyi... | https://arxiv.org/abs/2505.16965v1 |
I’ll play tennis tomorrow. US Open is a tennis tournament. Who is going to win the US Open? [Segment 4]: Suddenly, dark clouds appeared. Thunder rumbled in the distance. The rain poured down heavily. [Segment 5]: People ran for shelter. [Segment 6]: What are you doing? I am here working on my project. k= 7 segments : [... | https://arxiv.org/abs/2505.16965v1 |
[Segment 4]: I’ll play tennis tomorrow. US Open is a tennis tournament. Who is going to win the US Open? [Segment 5]: It was a beautiful morning. The rain poured down heavily. k= 6 segments :[Segment 1]: Suddenly, dark clouds appeared. Thunder rumbled in the distance. The rain poured down heavily. [Segment 2]: What are... | https://arxiv.org/abs/2505.16965v1 |
rumbled in the distance. The rain poured down heavily. People ran for shelter. [Segment 3]: I’ll play tennis tomorrow. US Open is a tennis tournament. Who is going to win the US Open? [Segment 4]: What are you doing? I am here working on my project. k= 5 segments :[Segment 1]: The sun was shining brightly. It was a bea... | https://arxiv.org/abs/2505.16965v1 |
using bi(xi) =ψi(xi) +m(T) i(xi) 13:end for 14:Final Segmentation: 15:foreach embedding Rido 16: Assign segment using x∗ i= arg maxxi∈{1,···,k}bi(xi). 17:end for 18:return Segment assignments {x∗ 1, . . . , x∗ n} 3–5 6–8 9–11 3–11 3–15 12–15 ARI NMI ARI NMI ARI NMI ARI NMI ARI NMI ARI NMI BP-Seg 0.10 0.04 0.08 0.04 0.0... | https://arxiv.org/abs/2505.16965v1 |
arXiv:2505.16967v1 [cs.IR] 22 May 2025Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval Nandan Thakur*Crystina Zhang*Xueguang Ma Jimmy Lin David R. Cheriton School of Computer Science, University of Waterloo, Canada Code: https://github.com/castorini/rlhn Data... | https://arxiv.org/abs/2505.16967v1 |
which are typically intro- duced by misclassifying unlabeled candidates as negative training examples. This is especially severe for sparsely-annotated retrieval datasets, such as MS MARCO (Nguyen et al., 2016) or NQ(Kwiatkowski et al., 2019). Figure 3 shows an example of a false negative present in HOT- POTQA(Yang et ... | https://arxiv.org/abs/2505.16967v1 |
than retrieval mod- els, yet does not remove the false negatives them- selves. As we will show in the results section, albeit smaller, inferior training data also negatively affect cross-encoders. The latter alleviates the issue based on the assumption that the relevance scores of false negatives are systematically hig... | https://arxiv.org/abs/2505.16967v1 |
Ground Truth or Positive LLM Judge CascadingRemaining Hard Negatives(False) Hard Negatives YesNo Relevance = 0Relevance = 1 Relevance = 1Exit NoExit Yes Cost Ef fective Accurate Training Dataset Instance Identified & Relabeled Hard NegativesRelevance = 0prompt promptFigure 2: Flowchart for RLHN (ReLabeling HardNegative... | https://arxiv.org/abs/2505.16967v1 |
Dataset Postprocessing & Statistics In Table 1, we show the training dataset statis- tics observed in the BGE training collection. MS MARCO contains the highest amount of training pairs, followed by HOTPOT QA. All datasets con- tain training pairs with 1–3 ground-truth passages and 13–25 hard negatives (except NQwith 9... | https://arxiv.org/abs/2505.16967v1 |
original dataset in fine-tuning without relabeling. 5BGE dataset: huggingface.co/datasets/cfli/bge-full-data 1234567891011121314150204060% of Training Pairs 57.63 % 18.67 % 8.93 % 5.19 % 3.23 % 1.94 % 1.32 % 0.88 % 0.59 % 0.46 % 0.32 % 0.24 % 0.17 % 0.12 % 0.09 %Avg. Distribution of False Hard NegativesFigure 3: The di... | https://arxiv.org/abs/2505.16967v1 |
0.391 0.382 0.384 0.367 0.370 0.373 0.360 SciFact 0.735 0.741 0.731 0.733 0.744 0.735 0.740 0.755 0.755 0.767 TREC-NEWS†0.465 0.470 0.466 0.473 0.464 0.473 0.484 0.494 0.480 0.487 Robust04†0.442 0.448 0.452 0.471 0.447 0.458 0.497 0.501 0.501 0.540 Signal-1M (RT)†0.275 0.279 0.275 0.275 0.274 0.270 0.274 0.275 0.268 0.... | https://arxiv.org/abs/2505.16967v1 |
→0.529 on 14 datasets on average in BEIR, by fine-tuning on al- most 2.35 ×smaller dataset (1.6M →680K). 5.2 Main Results: Relabeling False Negatives This section shows the results of the fine-tuned models on the variants of the training dataset de- scribed in Section 3.1 and 3.2, keeping the rest of the model training... | https://arxiv.org/abs/2505.16967v1 |
ArguAna 0.740 0.730 0.763 Touché-2020†0.275 0.308 0.313 DBPedia 0.532 0.536 0.538 SCIDOCS 0.278 0.273 0.270 FEVER 0.941 0.939 0.936 Climate-FEVER 0.457 0.468 0.430 SciFact 0.786 0.793 0.794 TREC-NEWS†0.507 0.513 0.527 Robust04†0.531 0.548 0.589 Signal-1M†0.292 0.276 0.274 BioASQ†0.510 0.505 0.500 Avg. 16 (All) 0.575 0.... | https://arxiv.org/abs/2505.16967v1 |
false negatives (labeled as positives) in the top-10 reranked results. P@L(GT) calculates the precision of false negatives present in top- kreranked results, where kvaries in each query, measuring the count of false negatives detected using RLHN. Reranker distillation is competitive, but lacks in detecting false negati... | https://arxiv.org/abs/2505.16967v1 |
focus on enduring culinary tra- ditions [ ... ]Food & Wine :Food &Wine isa monthly magazine published byTime Inc. Itwas founded in1978 byAri- aneandMichael Batterberry. Itfeatures recipes, cook ingtips, travel information, restau rantreviews, chefs, wine pairings andseasonal holidaycontent[...]Cocina (magazine) :isaCol... | https://arxiv.org/abs/2505.16967v1 |
limited number of queries, we observe that the ground truth passage can have conflicting informa- tion with the false negative, and can be incorrectly labeled. E.g., the correct answer to the (Q2) query asking about the professional ice hockey establish- ment is 1917, present within the false negative, and 1997, mentio... | https://arxiv.org/abs/2505.16967v1 |
large training datasets. The maximum training dataset size that we cov- ered in our work contained ≤1M training pairs. This is a reasonable dataset size to apply RLHN within a strict compute budget. Cleaning extremely large training datasets (for example, containing be- tween 1–10M training pairs) is not feasible, as i... | https://arxiv.org/abs/2505.16967v1 |
cost and improving performance. CoRR , abs/2305.05176. Chanyeol Choi, Junseong Kim, Seolhwa Lee, Jihoon Kwon, Sangmo Gu, Yejin Kim, Minkyung Cho, and Jy-yong Sohn. 2024. Linq-Embed-Mistral technical report. CoRR , abs/2412.03223. Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2023. Tevatron: An efficient and flexi... | https://arxiv.org/abs/2505.16967v1 |
analysis of the MSMARCO pas- sage collection. CoRR , abs/2112.03396. Gabriel Moreira, Radek Osmulski, Mengyao Xu, Ronay Ak, Benedikt Schifferer, and Even Oldridge. 2024. NV-Retriever: Improving text embedding mod- els with effective hard-negative mining. CoRR , abs/2407.15831. John Xavier Morris and Alexander M Rush. 2... | https://arxiv.org/abs/2505.16967v1 |
the 2022 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies , pages 2345–2360, Seattle, United States. Association for Computational Linguistics. Liang Wang, Nan Yang, Xiaolong Huang, Binx- ing Jiao, Linjun Yang, Daxin Jiang, Rangan Ma- jumder, and F... | https://arxiv.org/abs/2505.16967v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.