{"total":33,"rows":[{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2208.11646","title":"Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation","created":"2022-08-24","cited_by_count":75,"area":null},{"id":"2311.18702","title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","created":"2023-11-30","cited_by_count":66,"area":null},{"id":"2310.14564","title":"Language Models Hallucinate, but May Excel at Fact Verification","created":"2023-10-23","cited_by_count":37,"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":"2212.09171","title":"Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data","created":"2022-12-18","cited_by_count":21,"area":null},{"id":"2310.06282","title":"MuseChat: A Conversational Music Recommendation System for Videos","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2408.14622","title":"What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation","created":"2024-08-26","cited_by_count":17,"area":null},{"id":"2305.08566","title":"NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist","created":"2023-05-15","cited_by_count":16,"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":"2302.09852","title":"Unsupervised Layer-wise Score Aggregation for Textual OOD Detection","created":"2023-02-20","cited_by_count":15,"area":null},{"id":"2401.02749","title":"Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding","created":"2024-01-05","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":"2205.03589","title":"Learning Disentangled Textual Representations via Statistical Measures of Similarity","created":"2022-05-07","cited_by_count":14,"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":"2402.09766","title":"From Variability to Stability: Advancing RecSys Benchmarking Practices","created":"2024-02-15","cited_by_count":12,"area":null},{"id":"2310.14103","title":"Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications","created":"2023-10-21","cited_by_count":11,"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":"2307.06869","title":"DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2410.15268","title":"GraphNarrator: Generating Textual Explanations for Graph Neural Networks","created":"2024-10-20","cited_by_count":7,"area":null},{"id":"2209.13101","title":"WikiDes: A Wikipedia-Based Dataset for Generating Short Descriptions from Paragraphs","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2408.07706","title":"A Guide to Similarity Measures","created":"2024-08-07","cited_by_count":4,"area":null},{"id":"2604.09497","title":"BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2211.13527","title":"Beyond Mahalanobis-Based Scores for Textual OOD Detection","created":"2022-11-24","cited_by_count":3,"area":null},{"id":"2407.00453","title":"PerSEval: Assessing Personalization in Text Summarizers","created":"2024-06-29","cited_by_count":3,"area":null},{"id":"2204.13848","title":"Repro: An Open-Source Library for Improving the Reproducibility and Usability of Publicly Available Research Code","created":"2022-04-29","cited_by_count":2,"area":null},{"id":"2506.00448","title":"Fact-Controlled Diagnosis of Hallucinations in Medical Text Summarization","created":"2025-05-31","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":"2401.04522","title":"LUNA: A Framework for Language Understanding and Naturalness Assessment","created":"2024-01-09","cited_by_count":1,"area":null},{"id":"2601.10246","title":"coTherapist: A Behavior-Aligned Small Language Model to Support Mental Healthcare Experts","created":"2026-01-15","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":"2604.19261","title":"Towards a Linguistic Evaluation of Narratives: A Quantitative Stylistic Framework","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2606.29118","title":"An Information-Geometric Justification for Composite Coherence in Event-Based Narrative Extraction","created":"2026-06-28","cited_by_count":0,"area":null}],"next_cursor":null}