{"total":17,"rows":[{"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":"2602.00521","title":"Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory","created":"2026-01-31","cited_by_count":16,"area":null},{"id":"2503.06573","title":"WildIFEval: Instruction Following in the Wild","created":"2025-03-09","cited_by_count":11,"area":null},{"id":"2502.01754","title":"Evaluation of Large Language Models via Coupled Token Generation","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2603.16848","title":"Mediocrity is the key for LLM as a Judge Anchor Selection","created":"2026-03-17","cited_by_count":7,"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":"2506.05062","title":"Debatable Intelligence: Benchmarking LLM Judges via Debate Speech Evaluation","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2507.18392","title":"CLEAR: Error Analysis via LLM-as-a-Judge Made Easy","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2508.06111","title":"SKATE, a Scalable Tournament Eval: Weaker LLMs differentiate between stronger ones using verifiable challenges","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2605.21748","title":"RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.23628","title":"How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2608.10385","title":"Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2511.11597","title":"CLINB: A Climate Intelligence Benchmark for Foundational Models","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2603.01243","title":"Suffix-Constrained Greedy Search Algorithms for Causal Language Models","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.14400","title":"Extending Minimal Pairs with Ordinal Surprisal Curves and Entropy Across Applied Domains","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2610.02492","title":"Right Order, Wrong Scale: Auditing LLM Judges for Occupational AI Measurement","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.16814","title":"StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}