{"total":14,"rows":[{"id":"2405.01719","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2402.09766","title":"From Variability to Stability: Advancing RecSys Benchmarking Practices","created":"2024-02-15","cited_by_count":12,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2504.07749","title":"NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark","created":"2025-04-10","cited_by_count":8,"area":null},{"id":"2511.01066","title":"HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models","created":"2025-11-02","cited_by_count":7,"area":null},{"id":"2503.12613","title":"Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2411.00119","title":"Soft Condorcet Optimization for Ranking of General Agents","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2503.13102","title":"REPA: Russian Error Types Annotation for Evaluating Text Generation and Judgment Capabilities","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2506.09813","title":"Metritocracy: Representative Metrics for Lite Benchmarks","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2604.21769","title":"Who Defines \"Best\"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2502.03576","title":"Clone-Robust Weights in Metric Spaces: Handling Redundancy Bias for Benchmark Aggregation","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2602.07593","title":"Beyond Arrow: From Impossibility to Possibilities in Multi-Criteria Benchmarking","created":"2026-02-07","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":"2608.24477","title":"Dataset Scarcity Limits Robust Evaluation of Multilingual Embedding Models: A Case Study of Slavic Languages","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}