{"total":24,"rows":[{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"area":null},{"id":"2112.04139","title":"Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand","created":"2021-12-08","cited_by_count":32,"area":null},{"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":"2406.08723","title":"ECBD: Evidence-Centered Benchmark Design for NLP","created":"2024-06-13","cited_by_count":28,"area":null},{"id":"2203.07653","title":"Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness","created":"2022-03-15","cited_by_count":23,"area":null},{"id":"2112.00659","title":"Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines","created":"2021-12-01","cited_by_count":17,"area":null},{"id":"2203.03073","title":"ILDAE: Instance-Level Difficulty Analysis of Evaluation Data","created":"2022-03-07","cited_by_count":17,"area":null},{"id":"2210.05769","title":"Vote'n'Rank: Revision of Benchmarking with Social Choice Theory","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2412.06745","title":"ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities","created":"2024-12-09","cited_by_count":15,"area":null},{"id":"2210.12813","title":"TAPE: Assessing Few-shot Russian Language Understanding","created":"2022-10-23","cited_by_count":11,"area":null},{"id":"2606.08679","title":"Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation","created":"2026-06-07","cited_by_count":6,"area":null},{"id":"2304.09863","title":"End-User Development for Artificial Intelligence: A Systematic Literature Review","created":"2023-04-14","cited_by_count":4,"area":null},{"id":"2203.06404","title":"A Proposal to Study \"Is High Quality Data All We Need?\"","created":"2022-03-12","cited_by_count":2,"area":null},{"id":"2210.07663","title":"Pretrained Transformers Do not Always Improve Robustness","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2506.09813","title":"Metritocracy: Representative Metrics for Lite Benchmarks","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2106.06292","title":"A Discussion on Building Practical NLP Leaderboards: The Case of Machine Translation","created":"2021-06-11","cited_by_count":1,"area":null},{"id":"2210.07566","title":"A Survey of Parameters Associated with the Quality of Benchmarks in NLP","created":"2022-10-14","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":"2609.00482","title":"Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2210.04466","title":"Investigating the Failure Modes of the AUC metric and Exploring Alternatives for Evaluating Systems in Safety Critical Applications","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2304.06184","title":"LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversity","created":"2023-04-12","cited_by_count":0,"area":null}],"next_cursor":null}