{"total":486,"rows":[{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848,"area":null},{"id":"2402.04788","title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark","created":"2024-02-07","cited_by_count":372,"area":"mllm"},{"id":"2311.16452","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","created":"2023-11-28","cited_by_count":329,"area":null},{"id":"2406.07791","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","created":"2024-06-12","cited_by_count":269,"area":null},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238,"area":null},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2402.16786","title":"Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models","created":"2024-02-26","cited_by_count":162,"area":null},{"id":"2407.10362","title":"LAB-Bench: Measuring Capabilities of Language Models for Biology Research","created":"2024-07-14","cited_by_count":156,"area":null},{"id":"2405.01724","title":"Large Language Models are Inconsistent and Biased Evaluators","created":"2024-05-02","cited_by_count":153,"area":null},{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149,"area":"alignment"},{"id":"2411.00836","title":"DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models","created":"2024-10-29","cited_by_count":146,"area":"lr"},{"id":"2402.01781","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","created":"2024-02-01","cited_by_count":137,"area":null},{"id":"2406.05967","title":"CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark","created":"2024-06-10","cited_by_count":120,"area":"mllm"},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116,"area":"safety"},{"id":"2406.08446","title":"OLMES: A Standard for Language Model Evaluations","created":"2024-06-12","cited_by_count":106,"area":null},{"id":"2405.07467","title":"MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation","created":"2024-05-13","cited_by_count":105,"area":null},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2404.11457","title":"Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era","created":"2024-04-17","cited_by_count":98,"area":null},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2503.02199","title":"Words or Vision: Do Vision-Language Models Have Blind Faith in Text?","created":"2025-03-04","cited_by_count":89,"area":"mllm"},{"id":"2402.01789","title":"The Political Preferences of LLMs","created":"2024-02-02","cited_by_count":84,"area":null},{"id":"2508.17536","title":"Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?","created":"2025-08-24","cited_by_count":81,"area":"lr"},{"id":"2402.05119","title":"A Closer Look at the Limitations of Instruction Tuning","created":"2024-02-03","cited_by_count":77,"area":null},{"id":"2406.07545","title":"Open-LLM-Leaderboard: From Multi-choice to Open-style Questions for LLMs Evaluation, Benchmark, and Arena","created":"2024-06-11","cited_by_count":76,"area":null},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75,"area":"agents"},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74,"area":null},{"id":"2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","created":"2024-02-19","cited_by_count":71,"area":null},{"id":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2407.01100","title":"Eliminating Position Bias of Language Models: A Mechanistic Approach","created":"2024-07-01","cited_by_count":65,"area":null},{"id":"2410.02879","title":"Position: LLM Unlearning Benchmarks are Weak Measures of Progress","created":"2024-10-03","cited_by_count":63,"area":"safety"},{"id":"2410.18417","title":"Large Language Models Reflect the Ideology of their Creators","created":"2024-10-24","cited_by_count":57,"area":null},{"id":"2402.17649","title":"Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs","created":"2024-02-27","cited_by_count":55,"area":null},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54,"area":null},{"id":"2402.12071","title":"EmoBench: Evaluating the Emotional Intelligence of Large Language Models","created":"2024-02-19","cited_by_count":53,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2407.06576","title":"Virtual Personas for Language Models via an Anthology of Backstories","created":"2024-07-09","cited_by_count":51,"area":null},{"id":"2311.06233","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","created":"2023-11-10","cited_by_count":47,"area":null},{"id":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44,"area":null},{"id":"2406.19470","title":"Changing Answer Order Can Decrease MMLU Accuracy","created":"2024-06-27","cited_by_count":42,"area":null},{"id":"2504.18851","title":"When2Call: When (not) to Call Tools","created":"2025-04-26","cited_by_count":42,"area":"agents"},{"id":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41,"area":null},{"id":"2507.02856","title":"Answer Matching Outperforms Multiple Choice for Language Model Evaluation","created":"2025-07-03","cited_by_count":41,"area":null},{"id":"2407.03129","title":"Social Bias Evaluation for Large Language Models Requires Prompt Variations","created":"2024-07-03","cited_by_count":40,"area":null},{"id":"2502.11028","title":"Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models","created":"2025-02-16","cited_by_count":40,"area":null},{"id":"2507.04701","title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","created":"2025-07-07","cited_by_count":40,"area":null},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2504.03846","title":"Do LLM Evaluators Prefer Themselves for a Reason?","created":"2025-04-04","cited_by_count":38,"area":"lr"},{"id":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35,"area":null},{"id":"2410.15393","title":"CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2410.15413","title":"A Comprehensive Evaluation of Cognitive Biases in LLMs","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2503.05659","title":"A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval","created":"2025-03-07","cited_by_count":33,"area":"agents"},{"id":"2405.20612","title":"UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation","created":"2024-05-31","cited_by_count":31,"area":null},{"id":"2407.09141","title":"Accuracy is Not All You Need","created":"2024-07-12","cited_by_count":31,"area":null},{"id":"2503.21821","title":"Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving","created":"2025-03-26","cited_by_count":31,"area":null},{"id":"2510.15831","title":"VISTA: A Test-Time Self-Improving Video Generation Agent","created":"2025-10-17","cited_by_count":31,"area":null},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2406.15981","title":"Serial Position Effects of Large Language Models","created":"2024-06-23","cited_by_count":30,"area":null},{"id":"2402.13148","title":"Defending Jailbreak Prompts via In-Context Adversarial Game","created":"2024-02-20","cited_by_count":29,"area":"safety"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2312.11444","title":"An In-depth Look at Gemini's Language Abilities","created":"2023-12-18","cited_by_count":28,"area":null},{"id":"2405.11966","title":"Multiple-Choice Questions are Efficient and Robust LLM Evaluators","created":"2024-05-20","cited_by_count":28,"area":null},{"id":"2503.14996","title":"Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering","created":"2025-03-19","cited_by_count":28,"area":null},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2405.02743","title":"Beyond Performance: Quantifying and Mitigating Label Bias in LLMs","created":"2024-05-04","cited_by_count":25,"area":null},{"id":"2406.11370","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","created":"2024-06-17","cited_by_count":25,"area":"alignment"},{"id":"2409.05314","title":"Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications","created":"2024-09-09","cited_by_count":25,"area":null},{"id":"2609.26758","title":"Type-Safe Is Not Error-Free: Typed Decision Models Follow the Option Name, Not the Definition Bound to It","created":"2026-09-22","cited_by_count":25,"area":null},{"id":"2501.18081","title":"Normative Evaluation of Large Language Models with Everyday Moral Dilemmas","created":"2025-01-30","cited_by_count":24,"area":null},{"id":"2510.12697","title":"Multi-Agent Debate for LLM Judges with Adaptive Stability Detection","created":"2025-10-14","cited_by_count":23,"area":"lr"},{"id":"2401.07955","title":"A Study on Large Language Models' Limitations in Multiple-Choice Question Answering","created":"2024-01-15","cited_by_count":22,"area":null},{"id":"2406.17675","title":"Evaluating Large Language Models with Psychometrics","created":"2024-06-25","cited_by_count":22,"area":null},{"id":"2410.23609","title":"On Positional Bias of Faithfulness for Long-form Summarization","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2410.20245","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"area":null},{"id":"2406.03009","title":"Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models","created":"2024-06-05","cited_by_count":20,"area":null},{"id":"2410.04660","title":"KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA","created":"2024-10-07","cited_by_count":20,"area":"agents"},{"id":"2412.00323","title":"Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments","created":"2024-11-30","cited_by_count":20,"area":null},{"id":"2502.06666","title":"Automatic Evaluation of Healthcare LLMs Beyond Question-Answering","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2405.20421","title":"Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA","created":"2024-05-30","cited_by_count":19,"area":"mllm"},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2406.16469","title":"Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration","created":"2024-06-24","cited_by_count":19,"area":"mllm"},{"id":"2502.04134","title":"The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs","created":"2025-02-06","cited_by_count":19,"area":null},{"id":"2509.10704","title":"Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration","created":"2025-09-12","cited_by_count":19,"area":"agents"},{"id":"2311.08106","title":"Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models","created":"2023-11-14","cited_by_count":18,"area":null},{"id":"2402.18502","title":"Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification","created":"2024-02-28","cited_by_count":18,"area":null},{"id":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","cited_by_count":18,"area":null},{"id":"2407.06946","title":"Self-Recognition in Language Models","created":"2024-07-09","cited_by_count":18,"area":null},{"id":"2501.00555","title":"Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction","created":"2024-12-31","cited_by_count":18,"area":null},{"id":"2503.09598","title":"How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation","created":"2025-03-12","cited_by_count":18,"area":null},{"id":"2406.17600","title":"\"Seeing the Big through the Small\": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?","created":"2024-06-25","cited_by_count":17,"area":null},{"id":"2411.19504","title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering","created":"2024-11-29","cited_by_count":17,"area":null},{"id":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","cited_by_count":17,"area":"alignment"},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2408.07665","title":"Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models","created":"2024-08-14","cited_by_count":16,"area":null},{"id":"2412.11167","title":"Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette","created":"2024-12-15","cited_by_count":16,"area":"agents"},{"id":"2503.06987","title":"Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluations","created":"2025-03-10","cited_by_count":16,"area":null},{"id":"2506.23046","title":"SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions","created":"2025-06-29","cited_by_count":16,"area":null},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2405.03205","title":"Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions","created":"2024-05-06","cited_by_count":15,"area":"mechinterp"}],"next_cursor":"100"}