{"total":28,"rows":[{"id":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71,"area":null},{"id":"2201.11176","title":"DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence","created":"2022-01-26","cited_by_count":36,"area":null},{"id":"2412.09569","title":"JuStRank: Benchmarking LLM Judges for System Ranking","created":"2024-12-12","cited_by_count":29,"area":null},{"id":"2310.14424","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","created":"2023-10-22","cited_by_count":18,"area":null},{"id":"2406.15267","title":"Evaluating Diversity in Automatic Poetry Generation","created":"2024-06-21","cited_by_count":17,"area":null},{"id":"2305.14702","title":"DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","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":"2305.10284","title":"Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks","created":"2023-05-17","cited_by_count":14,"area":null},{"id":"2203.10012","title":"Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges","created":"2022-03-18","cited_by_count":13,"area":null},{"id":"2208.14585","title":"The Glass Ceiling of Automatic Evaluation in Natural Language Generation","created":"2022-08-31","cited_by_count":10,"area":null},{"id":"2205.01416","title":"Exact Paired-Permutation Testing for Structured Test Statistics","created":"2022-05-03","cited_by_count":6,"area":null},{"id":"2205.10019","title":"Translating Hanja Historical Documents to Contemporary Korean and English","created":"2022-05-20","cited_by_count":6,"area":null},{"id":"2301.01269","title":"Average Is Not Enough: Caveats of Multilingual Evaluation","created":"2023-01-03","cited_by_count":5,"area":null},{"id":"2205.10012","title":"Descartes: Generating Short Descriptions of Wikipedia Articles","created":"2022-05-20","cited_by_count":4,"area":null},{"id":"2404.13020","title":"Stronger Random Baselines for In-Context Learning","created":"2024-04-19","cited_by_count":4,"area":null},{"id":"2602.11318","title":"The Consensus Trap: Dissecting Subjectivity and the \"Ground Truth\" Illusion in Data Annotation","created":"2026-02-11","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":"2601.04925","title":"Can AI-Generated Persuasion Be Detected? Persuaficial Benchmark and AI vs. Human Linguistic Differences","created":"2026-01-08","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":"2202.03799","title":"What are the best systems? New perspectives on NLP Benchmarking","created":"2022-02-08","cited_by_count":0,"area":null},{"id":"2509.15098","title":"TextMineX: Data, Evaluation Framework and Ontology-guided LLM Pipeline for Humanitarian Mine Action","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2511.12290","title":"AugAbEx: Bridging Abstractive and Extractive Legal Summarization","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2512.24145","title":"When Does Pairing Seeds Reduce Variance? Evidence from a Multi-Agent Economic Simulation","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2605.12395","title":"A Comparative Study of Controlled Text Generation Systems Using Level-Playing-Field Evaluation Principles","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.21359","title":"Does Finetuning with Scientific Data Increase Hallucinations? A Multi-domain Factuality Evaluation of LLMs","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.09957","title":"Workload-Driven Optimization for On-Device Real-Time Subtitle Translation","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.18108","title":"Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation","created":"2026-06-10","cited_by_count":0,"area":null}],"next_cursor":null}