{"total":137,"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":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238,"area":null},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2407.10457","title":"The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism","created":"2024-07-15","cited_by_count":116,"area":null},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114,"area":null},{"id":"2402.18060","title":"Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions","created":"2024-02-28","cited_by_count":109,"area":null},{"id":"2406.08446","title":"OLMES: A Standard for Language Model Evaluations","created":"2024-06-12","cited_by_count":106,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"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":"2402.19379","title":"Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy","created":"2024-02-29","cited_by_count":67,"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":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2404.09937","title":"Compression Represents Intelligence Linearly","created":"2024-04-15","cited_by_count":56,"area":null},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54,"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":"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":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35,"area":null},{"id":"2502.14074","title":"Investigating Non-Transitivity in LLM-as-a-Judge","created":"2025-02-19","cited_by_count":34,"area":"agents"},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2404.16966","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks","created":"2024-04-25","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":"2405.01719","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2406.08723","title":"ECBD: Evidence-Centered Benchmark Design for NLP","created":"2024-06-13","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":"2404.04298","title":"SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses","created":"2024-04-04","cited_by_count":26,"area":"synth"},{"id":"2410.23609","title":"On Positional Bias of Faithfulness for Long-form Summarization","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2412.03597","title":"The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?","created":"2024-12-02","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":"2503.01622","title":"DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2502.06666","title":"Automatic Evaluation of Healthcare LLMs Beyond Question-Answering","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2402.13887","title":"Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models","created":"2024-02-21","cited_by_count":19,"area":null},{"id":"2503.00137","title":"SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models","created":"2025-02-28","cited_by_count":19,"area":null},{"id":"2504.18574","title":"Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism","created":"2025-04-22","cited_by_count":15,"area":null},{"id":"2506.19468","title":"MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages","created":"2025-06-24","cited_by_count":15,"area":null},{"id":"2410.09247","title":"Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts","created":"2024-10-11","cited_by_count":14,"area":null},{"id":"2509.03986","title":"Promptception: How Sensitive Are Large Multimodal Models to Prompts?","created":"2025-09-04","cited_by_count":13,"area":"mllm"},{"id":"2510.09869","title":"NarraBench: A Comprehensive Framework for Narrative Benchmarking","created":"2025-10-10","cited_by_count":13,"area":null},{"id":"2404.00699","title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2412.17874","title":"Evaluating LLM Reasoning in the Operations Research Domain with ORQA","created":"2024-12-22","cited_by_count":12,"area":"lr"},{"id":"2507.03483","title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset","created":"2025-07-04","cited_by_count":12,"area":"lr"},{"id":"2506.03101","title":"Beyond Text Compression: Evaluating Tokenizers Across Scales","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2604.11581","title":"Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking","created":"2026-04-13","cited_by_count":10,"area":null},{"id":"2410.11672","title":"Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2410.22118","title":"The Impact of Inference Acceleration on Bias of LLMs","created":"2024-10-29","cited_by_count":9,"area":"inference"},{"id":"2510.11905","title":"LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2507.13490","title":"Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2509.19364","title":"The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behavior","created":"2025-09-18","cited_by_count":8,"area":null},{"id":"2604.16403","title":"Computational Hermeneutics: Evaluating generative AI as a cultural technology","created":"2026-03-31","cited_by_count":8,"area":null},{"id":"2512.17875","title":"Visually Prompted Benchmarks Are Surprisingly Fragile","created":"2025-12-19","cited_by_count":7,"area":null},{"id":"2404.12535","title":"Is There No Such Thing as a Bad Question? H4R: HalluciBot For Ratiocination, Rewriting, Ranking, and Routing","created":"2024-04-18","cited_by_count":6,"area":null},{"id":"2406.06581","title":"Order-Independence Without Fine Tuning","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2407.04065","title":"On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2506.10491","title":"Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2503.01550","title":"None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answering","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2503.10673","title":"ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2504.12562","title":"ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2507.01785","title":"MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2602.06221","title":"BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2502.12459","title":"Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2503.04840","title":"Framing the Game: How Context Shapes LLM Decision-Making","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2503.19120","title":"Where is this coming from? Making groundedness count in the evaluation of Document VQA models","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2510.14773","title":"Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning","created":"2025-10-16","cited_by_count":4,"area":"lr"},{"id":"2602.17316","title":"Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation","created":"2026-02-19","cited_by_count":4,"area":null},{"id":"2410.18991","title":"TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty Simulations","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2502.08662","title":"RoToR: Towards More Reliable Responses for Order-Invariant Inputs","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2505.03563","title":"Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework","created":"2025-05-06","cited_by_count":3,"area":null},{"id":"2505.12938","title":"Leveraging LLM Inconsistency to Boost Pass@k Performance","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2507.14913","title":"PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation","created":"2025-07-20","cited_by_count":3,"area":null},{"id":"2509.22506","title":"Representing LLMs in Prompt Semantic Task Space","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2510.14242","title":"Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2601.13183","title":"OpenExempt: A Diagnostic Benchmark for Legal Reasoning and a Framework for Creating Custom Benchmarks on Demand","created":"2026-01-19","cited_by_count":3,"area":"lr"},{"id":"2602.03238","title":"\"LLM Agent Performance\" Is Not a Single Evaluation Target","created":"2026-02-03","cited_by_count":3,"area":"agents"},{"id":"2602.04297","title":"Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2609.09218","title":"The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean","created":"2026-09-06","cited_by_count":3,"area":"agents"},{"id":"2412.10558","title":"Too Big to Fool: Resisting Deception in Language Models","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2502.18798","title":"Choices Speak Louder than Questions","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2503.23483","title":"Order Independence With Finetuning","created":"2025-03-30","cited_by_count":2,"area":null},{"id":"2510.19678","title":"I Spy With My Model's Eye: Visual Search as a Behavioural Test for MLLMs","created":"2025-10-22","cited_by_count":2,"area":"mllm"},{"id":"2602.00723","title":"Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2602.03344","title":"Robustness as an Emergent Property of Task Performance","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2604.07733","title":"CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V","created":"2026-04-09","cited_by_count":2,"area":"agents"},{"id":"2607.02587","title":"The Moving Target: A Longitudinal Audit of Trust-Benchmark Score Drift Across Open-Source Chat LLM Release Lines","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2410.00179","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2410.02343","title":"Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2412.04277","title":"Arabic Stable LM: Adapting Stable LM 2 1.6B to Arabic","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2506.07658","title":"From Raw Corpora to Domain Benchmarks: Automated Evaluation of LLM Domain Expertise","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2509.12678","title":"Instance-level Randomization: Toward More Stable LLM Evaluations","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2511.17405","title":"Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT","created":"2025-11-21","cited_by_count":1,"area":"mllm"},{"id":"2511.22341","title":"Unexplored flaws in multiple-choice VQA make benchmarking unreliable","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2602.01017","title":"How Does Unfaithful Reasoning Emerge from Autoregressive Training? A Study of Synthetic Experiments","created":"2026-02-01","cited_by_count":1,"area":"lr"},{"id":"2606.03237","title":"Solipsistic Superintelligence is Unlikely to be Cooperative","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.10657","title":"Are We Evaluating Knowledge or Phrasing? Mitigating MCQA Sensitivity with ParaEval","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2607.02586","title":"Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.22554","title":"Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2608.17516","title":"Effects of Answer Format Variation on Gender Bias in Large Language Models","created":"2026-08-18","cited_by_count":1,"area":null}],"next_cursor":"100"}