{"total":21,"rows":[{"id":"2506.07673","title":"How Benchmark Prediction from Fewer Data Misses the Mark","created":"2025-06-09","cited_by_count":28,"area":null},{"id":"2601.20251","title":"Efficient Evaluation of LLM Performance with Statistical Guarantees","created":"2026-01-28","cited_by_count":18,"area":null},{"id":"2510.08730","title":"How Reliable is Language Model Micro-Benchmarking?","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2508.10175","title":"Estimating Machine Translation Difficulty","created":"2025-08-13","cited_by_count":6,"area":null},{"id":"2510.17998","title":"SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone","created":"2025-10-20","cited_by_count":6,"area":null},{"id":"2602.06221","title":"BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2603.21840","title":"Select, Label, Evaluate: Active Testing in NLP","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2509.26619","title":"Searching the Internet for Challenging Benchmarks at Scale","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2509.26592","title":"Generating Difficult-to-Translate Texts","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2601.18006","title":"PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2601.22157","title":"Discovering Hidden Gems in Model Repositories","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","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":"2608.03437","title":"Dynamically Allocating Evaluation Effort for Model Ranking","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2609.04173","title":"Last Translation Benchmark","created":"2026-09-03","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":"2603.21438","title":"PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2609.04959","title":"Discourse Dependency: A Continuous Criterion for Translation Difficulty","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.05949","title":"The Blindness of Document-Level Translation Evaluation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2610.01627","title":"What Makes Something Hard(er)? Explaining Question Difficulty in Natural Language","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}