{"total":18,"rows":[{"id":"2405.17202","title":"Efficient multi-prompt evaluation of LLMs","created":"2024-05-27","cited_by_count":73,"area":null},{"id":"2412.09569","title":"JuStRank: Benchmarking LLM Judges for System Ranking","created":"2024-12-12","cited_by_count":29,"area":null},{"id":"2501.18251","title":"How to Select Datapoints for Efficient Human Evaluation of NLG Models?","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2408.03573","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","created":"2024-08-07","cited_by_count":17,"area":null},{"id":"2508.09093","title":"Scaling Up Active Testing to Large Language Models","created":"2025-08-12","cited_by_count":13,"area":null},{"id":"2510.08730","title":"How Reliable is Language Model Micro-Benchmarking?","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2410.13569","title":"Learning on Model Weights using Tree Experts","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2407.01878","title":"Compare without Despair: Reliable Preference Evaluation with Generation Separability","created":"2024-07-02","cited_by_count":4,"area":null},{"id":"2603.19264","title":"Generative Active Testing: Efficient LLM Evaluation via Proxy Task Adaptation","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2604.23099","title":"ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation","created":"2026-04-25","cited_by_count":2,"area":null},{"id":"2607.08522","title":"Stop Guessing When to Stop Testing: Efficient Model Evaluation with Just Enough Data","created":"2026-07-09","cited_by_count":2,"area":null},{"id":"2601.22157","title":"Discovering Hidden Gems in Model Repositories","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2605.24981","title":"Large Language Model Selection with Limited Annotations","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2607.08347","title":"Prediction-Powered Active Testing","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2510.09418","title":"Large Language Model Selection with Limited Annotations","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2602.07226","title":"Fault-Tolerant Evaluation for Sample-Efficient Model Performance Estimators","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2610.01592","title":"Which LLM to pick? Online Active Model Selection for Large Language Models","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.18248","title":"Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}