{"total":205,"rows":[{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500,"area":null},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318,"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":"2605.00674","title":"Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs","created":"2026-05-01","cited_by_count":137,"area":null},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105,"area":null},{"id":"2406.11657","title":"Can LLM be a Personalized Judge?","created":"2024-06-17","cited_by_count":100,"area":null},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2410.03608","title":"TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation","created":"2024-10-04","cited_by_count":68,"area":null},{"id":"2505.23802","title":"MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks","created":"2025-05-26","cited_by_count":64,"area":null},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54,"area":null},{"id":"2506.07962","title":"Correlated Errors in Large Language Models","created":"2025-06-09","cited_by_count":45,"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":"2510.27106","title":"Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks","created":"2025-10-31","cited_by_count":38,"area":null},{"id":"2411.06176","title":"M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework","created":"2024-11-09","cited_by_count":36,"area":null},{"id":"2508.06709","title":"Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judge","created":"2025-08-08","cited_by_count":36,"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":"2505.12201","title":"How Reliable is Multilingual LLM-as-a-Judge?","created":"2025-05-18","cited_by_count":30,"area":null},{"id":"2606.19544","title":"Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias","created":"2026-06-17","cited_by_count":28,"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":"2605.29800","title":"Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels","created":"2026-05-28","cited_by_count":26,"area":null},{"id":"2408.09235","title":"Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA","created":"2024-08-17","cited_by_count":25,"area":null},{"id":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"id":"2506.18203","title":"Shrinking the Generation-Verification Gap with Weak Verifiers","created":"2025-06-22","cited_by_count":24,"area":null},{"id":"2405.13684","title":"CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models","created":"2024-05-22","cited_by_count":18,"area":null},{"id":"2410.11594","title":"Black-box Uncertainty Quantification Method for LLM-as-a-Judge","created":"2024-10-15","cited_by_count":18,"area":null},{"id":"2504.19254","title":"Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers","created":"2025-04-27","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":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2504.11972","title":"Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses","created":"2025-04-16","cited_by_count":14,"area":null},{"id":"2410.15512","title":"Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?","created":"2024-10-20","cited_by_count":13,"area":null},{"id":"2504.09714","title":"Evaluating the Quality of Benchmark Datasets for Low-Resource Languages: A Case Study on Turkish","created":"2025-04-13","cited_by_count":13,"area":null},{"id":"2603.00039","title":"CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation","created":"2026-02-09","cited_by_count":13,"area":null},{"id":"2606.14199","title":"OdysSim: Building Foundation Models for Human Behavior Simulation","created":"2026-06-12","cited_by_count":13,"area":null},{"id":"2503.06573","title":"WildIFEval: Instruction Following in the Wild","created":"2025-03-09","cited_by_count":11,"area":null},{"id":"2601.19532","title":"Benchmarks Saturate When The Model Gets Smarter Than The Judge","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2604.06996","title":"Self-Preference Bias in Rubric-Based Evaluation of Large Language Models","created":"2026-04-08","cited_by_count":11,"area":null},{"id":"2409.06820","title":"PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation","created":"2024-09-10","cited_by_count":10,"area":null},{"id":"2502.17591","title":"Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2607.28802","title":"Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures","created":"2026-07-30","cited_by_count":10,"area":null},{"id":"2503.04804","title":"What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2503.17755","title":"Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes","created":"2025-03-22","cited_by_count":9,"area":null},{"id":"2507.17015","title":"Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge?","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2509.00591","title":"Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness","created":"2025-08-30","cited_by_count":9,"area":null},{"id":"2502.20170","title":"Re-evaluating Open-ended Evaluation of Large Language Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2604.23178","title":"Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines","created":"2026-04-25","cited_by_count":8,"area":null},{"id":"2408.14960","title":"Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2502.18018","title":"Verdict: A Library for Scaling Judge-Time Compute","created":"2025-02-25","cited_by_count":7,"area":null},{"id":"2506.22157","title":"Training Language Model to Critique for Better Refinement","created":"2025-06-27","cited_by_count":7,"area":null},{"id":"2507.17216","title":"The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2601.08654","title":"From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges","created":"2026-01-13","cited_by_count":7,"area":null},{"id":"2602.16610","title":"Who can we trust? LLM-as-a-jury for Comparative Assessment","created":"2026-02-18","cited_by_count":7,"area":null},{"id":"2410.09012","title":"Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2410.10215","title":"SkillAggregation: Reference-free LLM-Dependent Aggregation","created":"2024-10-14","cited_by_count":6,"area":null},{"id":"2503.08327","title":"Adding Chocolate to Mint: Mitigating Metric Interference in Machine Translation","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2503.08542","title":"CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2606.00093","title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2609.29769","title":"Decision Models vs. LLMs as Rubric Judges: Cheaper, Faster, and Wrong in the Same Places","created":"2026-09-24","cited_by_count":6,"area":null},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2411.13187","title":"Engagement-Driven Content Generation with Large Language Models","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2504.02323","title":"CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring and Feedback","created":"2025-04-03","cited_by_count":5,"area":null},{"id":"2507.04815","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2510.00628","title":"Hearing the Order: Investigating Position Bias in Large Audio-Language Models","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2606.28960","title":"Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries","created":"2026-06-27","cited_by_count":5,"area":null},{"id":"2407.17022","title":"Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education","created":"2024-07-24","cited_by_count":4,"area":null},{"id":"2502.00322","title":"MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2503.11858","title":"OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2504.09394","title":"Evaluation Under Imperfect Benchmarks and Ratings: A Case Study in Text Simplification","created":"2025-04-13","cited_by_count":4,"area":null},{"id":"2505.21959","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2505.21972","title":"LLMs Judging LLMs: A Simplex Perspective","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2510.25384","title":"Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2603.01865","title":"CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2604.00136","title":"ParetoBandit: Budget-Paced Adaptive Routing for Non-Stationary LLM Serving","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2604.18547","title":"FUSE: Ensembling Verifiers with Zero Labeled Data","created":"2026-04-20","cited_by_count":4,"area":null},{"id":"2406.04752","title":"CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2411.05775","title":"Fact or Fiction? Can LLMs be Reliable Annotators for Political Truths?","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2507.07787","title":"Measuring AI Alignment with Human Flourishing","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2508.00454","title":"Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple LLM Judges","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2509.14899","title":"CARGO: A Framework for Confidence-Aware Routing of Large Language Models","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2601.05376","title":"The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2601.14698","title":"ClaimDB: A Fact Verification Benchmark over Large Structured Data","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2601.17312","title":"Meta-Judging with Large Language Models: Concepts, Methods, and Challenges","created":"2026-01-24","cited_by_count":3,"area":null},{"id":"2603.23990","title":"From Untamed Black Box to Interpretable Pedagogical Orchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2604.02359","title":"Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2606.07810","title":"SLMJury: Can Small Language Models Judge as Well as Large Ones?","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2411.08010","title":"ExpressivityBench: Can LLMs Communicate Implicitly?","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2504.07385","title":"SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA","created":"2025-04-10","cited_by_count":2,"area":null},{"id":"2508.01401","title":"MedSynth: Realistic, Synthetic Medical Dialogue-Note Pairs","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2509.19880","title":"Do Before You Judge: Self-Reference as a Pathway to Better LLM Evaluation","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.03541","title":"What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2603.09452","title":"CyberThreat-Eval: Can Large Language Models Automate Real-World Threat Research?","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2604.22313","title":"CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.01311","title":"The Partial Testimony of Logs: Evaluation of Language Model Generation under Confounded Model Choice","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.12199","title":"Overtrained, Not Misaligned","created":"2026-05-12","cited_by_count":2,"area":null}],"next_cursor":"100"}