{"total":24,"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":"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":"2408.15204","title":"Can Unconfident LLM Annotations Be Used for Confident Conclusions?","created":"2024-08-27","cited_by_count":49,"area":null},{"id":"2601.20913","title":"Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges","created":"2026-01-28","cited_by_count":24,"area":null},{"id":"2506.07949","title":"Cost-Optimal Active AI Model Evaluation","created":"2025-06-09","cited_by_count":19,"area":null},{"id":"2502.04294","title":"Prediction-Powered E-Values","created":"2025-02-06","cited_by_count":16,"area":null},{"id":"2603.27414","title":"Multiple-Prediction-Powered Inference","created":"2026-03-28","cited_by_count":9,"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":"2509.22957","title":"Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas","created":"2025-09-26","cited_by_count":8,"area":null},{"id":"2509.20345","title":"General Synthetic-Powered Inference","created":"2025-09-24","cited_by_count":6,"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":"2505.21972","title":"LLMs Judging LLMs: A Simplex Perspective","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2604.18569","title":"Revisiting Active Sequential Prediction-Powered Mean Estimation","created":"2026-04-20","cited_by_count":4,"area":null},{"id":"2512.05456","title":"Do We Really Even Need Data? A Modern Look at Drawing Inference with Predicted Data","created":"2025-12-05","cited_by_count":3,"area":null},{"id":"2605.15761","title":"A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2606.13221","title":"From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2510.20387","title":"Relative-Based Scaling Law for Neural Language Models","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2608.26638","title":"Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.32248","title":"Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2605.08069","title":"Empirical Bayes Rebiasing","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.11638","title":"Learning U-Statistics with Active Inference","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.05052","title":"Beyond Independent Labels: Schwartz-Geometry Decoding for Human Value Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.24629","title":"Augmented Hypothesis Testing with Persona-Based LLM Simulations","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.01317","title":"Prediction-powered Neural Architecture Search","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}