{"total":723,"rows":[{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120,"area":null},{"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":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468,"area":null},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262,"area":null},{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243,"area":null},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205,"area":null},{"id":"2411.00640","title":"Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations","created":"2024-11-01","cited_by_count":148,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2406.08478","title":"What If We Recaption Billions of Web Images with LLaMA-3?","created":"2024-06-12","cited_by_count":87,"area":null},{"id":"2406.04485","title":"GenAI Arena: An Open Evaluation Platform for Generative Models","created":"2024-06-06","cited_by_count":82,"area":null},{"id":"2406.06565","title":"MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures","created":"2024-06-03","cited_by_count":74,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69,"area":null},{"id":"2503.21248","title":"ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition","created":"2025-03-27","cited_by_count":66,"area":null},{"id":"2510.20270","title":"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases","created":"2025-10-23","cited_by_count":65,"area":null},{"id":"2506.18123","title":"RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies","created":"2025-06-22","cited_by_count":64,"area":null},{"id":"2509.26468","title":"fev-bench: A Realistic Benchmark for Time Series Forecasting","created":"2025-09-30","cited_by_count":64,"area":null},{"id":"2501.10326","title":"Large language models for automated scholarly paper review: A survey","created":"2025-01-17","cited_by_count":61,"area":null},{"id":"2409.15254","title":"Archon: An Architecture Search Framework for Inference-Time Techniques","created":"2024-09-23","cited_by_count":60,"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":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","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":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51,"area":null},{"id":"2407.00379","title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation","created":"2024-06-29","cited_by_count":49,"area":null},{"id":"2509.00496","title":"ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics","created":"2025-08-30","cited_by_count":49,"area":null},{"id":"2410.02223","title":"EmbedLLM: Learning Compact Representations of Large Language Models","created":"2024-10-03","cited_by_count":48,"area":null},{"id":"2406.07882","title":"Designing a Dashboard for Transparency and Control of Conversational AI","created":"2024-06-12","cited_by_count":46,"area":null},{"id":"2410.07137","title":"Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates","created":"2024-10-09","cited_by_count":45,"area":null},{"id":"2503.05336","title":"Toward an Evaluation Science for Generative AI Systems","created":"2025-03-07","cited_by_count":45,"area":null},{"id":"2408.10365","title":"AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviews","created":"2024-08-19","cited_by_count":44,"area":null},{"id":"2410.16256","title":"CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution","created":"2024-10-21","cited_by_count":42,"area":null},{"id":"2412.15194","title":"MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark","created":"2024-12-19","cited_by_count":41,"area":null},{"id":"2502.18968","title":"Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles","created":"2025-02-26","cited_by_count":41,"area":null},{"id":"2503.12329","title":"CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era","created":"2025-03-16","cited_by_count":41,"area":null},{"id":"2506.01048","title":"IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory","created":"2025-06-01","cited_by_count":40,"area":null},{"id":"2503.05142","title":"RocketEval: Efficient Automated LLM Evaluation via Grading Checklist","created":"2025-03-07","cited_by_count":39,"area":null},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"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":"2412.05631","title":"CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds","created":"2024-12-07","cited_by_count":38,"area":null},{"id":"2510.27106","title":"Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks","created":"2025-10-31","cited_by_count":38,"area":null},{"id":"2406.15053","title":"PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data","created":"2024-06-21","cited_by_count":37,"area":null},{"id":"2410.19317","title":"FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs","created":"2024-10-25","cited_by_count":36,"area":null},{"id":"2502.14815","title":"Optimizing Model Selection for Compound AI Systems","created":"2025-02-20","cited_by_count":36,"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":"2406.13469","title":"Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks","created":"2024-06-19","cited_by_count":34,"area":null},{"id":"2504.07114","title":"ChatBench: From Static Benchmarks to Human-AI Evaluation","created":"2025-03-22","cited_by_count":34,"area":null},{"id":"2506.05334","title":"Search Arena: Analyzing Search-Augmented LLMs","created":"2025-06-05","cited_by_count":34,"area":null},{"id":"2502.12150","title":"Idiosyncrasies in Large Language Models","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2508.15734","title":"Measuring the environmental impact of delivering AI at Google Scale","created":"2025-08-21","cited_by_count":32,"area":null},{"id":"2506.02592","title":"Beyond the Surface: Measuring Self-Preference in LLM Judgments","created":"2025-06-03","cited_by_count":31,"area":null},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"area":null},{"id":"2408.08808","title":"Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge","created":"2024-08-16","cited_by_count":30,"area":null},{"id":"2410.02677","title":"CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming","created":"2024-10-03","cited_by_count":30,"area":null},{"id":"2412.13575","title":"Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement","created":"2024-12-18","cited_by_count":30,"area":null},{"id":"2502.14855","title":"Prompt-to-Leaderboard","created":"2025-02-20","cited_by_count":30,"area":null},{"id":"2510.12720","title":"Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception","created":"2025-10-14","cited_by_count":30,"area":null},{"id":"2511.21140","title":"How to Correctly Report LLM-as-a-Judge Evaluations","created":"2025-11-26","cited_by_count":30,"area":null},{"id":"2412.09569","title":"JuStRank: Benchmarking LLM Judges for System Ranking","created":"2024-12-12","cited_by_count":29,"area":null},{"id":"2503.13975","title":"Navigating Rifts in Human-LLM Grounding: Study and Benchmark","created":"2025-03-18","cited_by_count":29,"area":null},{"id":"2410.19008","title":"Teach Multimodal LLMs to Comprehend Electrocardiographic Images","created":"2024-10-21","cited_by_count":28,"area":null},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2407.02397","title":"Learning to Refine with Fine-Grained Natural Language Feedback","created":"2024-07-02","cited_by_count":27,"area":null},{"id":"2411.06032","title":"LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output","created":"2024-11-09","cited_by_count":27,"area":null},{"id":"2503.08893","title":"EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees","created":"2025-03-11","cited_by_count":27,"area":null},{"id":"2406.04291","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2407.10627","title":"Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2503.09347","title":"Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts","created":"2025-03-12","cited_by_count":26,"area":null},{"id":"2505.20139","title":"StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs","created":"2025-05-26","cited_by_count":25,"area":null},{"id":"2409.08775","title":"What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use","created":"2024-09-13","cited_by_count":24,"area":null},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2508.21141","title":"Adaptive LLM Routing under Budget Constraints","created":"2025-08-28","cited_by_count":24,"area":null},{"id":"2406.06369","title":"Annotation alignment: Comparing LLM and human annotations of conversational safety","created":"2024-06-10","cited_by_count":23,"area":null},{"id":"2502.07346","title":"BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models","created":"2025-02-11","cited_by_count":23,"area":null},{"id":"2509.26625","title":"Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training","created":"2025-09-30","cited_by_count":23,"area":null},{"id":"2405.17044","title":"Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders","created":"2024-05-27","cited_by_count":22,"area":null},{"id":"2410.07069","title":"ReIFE: Re-evaluating Instruction-Following Evaluation","created":"2024-10-09","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":"2510.00202","title":"RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers","created":"2025-09-30","cited_by_count":22,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2409.08466","title":"Explaining Datasets in Words: Statistical Models with Natural Language Parameters","created":"2024-09-13","cited_by_count":21,"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":"2502.11021","title":"Leveraging Uncertainty Estimation for Efficient LLM Routing","created":"2025-02-16","cited_by_count":21,"area":null},{"id":"2505.11065","title":"Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking","created":"2025-05-16","cited_by_count":21,"area":null},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2410.02653","title":"Measuring and Improving Persuasiveness of Large Language Models","created":"2024-10-03","cited_by_count":20,"area":null},{"id":"2501.07493","title":"Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards","created":"2025-01-13","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":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2507.01001","title":"SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks","created":"2025-07-01","cited_by_count":20,"area":null},{"id":"2510.26787","title":"Remote Labor Index: Measuring AI Automation of Remote Work","created":"2025-10-30","cited_by_count":20,"area":null},{"id":"2406.11044","title":"Evaluating the Performance of Large Language Models via Debates","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2410.22446","title":"Do Large Language Models Align with Core Mental Health Counseling Competencies?","created":"2024-10-29","cited_by_count":19,"area":null},{"id":"2501.15595","title":"SedarEval: Automated Evaluation using Self-Adaptive Rubrics","created":"2025-01-26","cited_by_count":19,"area":null},{"id":"2502.05714","title":"Proving the Coding Interview: A Benchmark for Formally Verified Code Generation","created":"2025-02-08","cited_by_count":19,"area":null},{"id":"2506.07949","title":"Cost-Optimal Active AI Model Evaluation","created":"2025-06-09","cited_by_count":19,"area":null}],"next_cursor":"100"}