{"total":35,"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":"2112.01589","title":"InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation","created":"2021-12-02","cited_by_count":33,"area":null},{"id":"2405.13769","title":"Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation","created":"2024-05-22","cited_by_count":32,"area":null},{"id":"2201.12245","title":"Wasserstein Iterative Networks for Barycenter Estimation","created":"2022-01-28","cited_by_count":23,"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":"2205.09630","title":"Acceptability Judgements via Examining the Topology of Attention Maps","created":"2022-05-19","cited_by_count":19,"area":null},{"id":"2208.07316","title":"MENLI: Robust Evaluation Metrics from Natural Language Inference","created":"2022-08-15","cited_by_count":18,"area":null},{"id":"2203.07921","title":"Unsupervised Extractive Opinion Summarization Using Sparse Coding","created":"2022-03-15","cited_by_count":17,"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":"2109.00922","title":"Improving Multimodal fusion via Mutual Dependency Maximisation","created":"2021-08-31","cited_by_count":15,"area":null},{"id":"2202.10062","title":"USCORE: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation","created":"2022-02-21","cited_by_count":15,"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":"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":"2310.18122","title":"OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization","created":"2023-10-27","cited_by_count":13,"area":null},{"id":"2110.03389","title":"Beam Search with Bidirectional Strategies for Neural Response Generation","created":"2021-10-07","cited_by_count":12,"area":null},{"id":"2310.01105","title":"Energy-Guided Continuous Entropic Barycenter Estimation for General Costs","created":"2023-10-02","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":"2201.12195","title":"Measure Estimation in the Barycentric Coding Model","created":"2022-01-28","cited_by_count":9,"area":null},{"id":"2204.00004","title":"Reproducibility Issues for BERT-based Evaluation Metrics","created":"2022-03-30","cited_by_count":9,"area":null},{"id":"2304.01680","title":"Can BERT eat RuCoLA? Topological Data Analysis to Explain","created":"2023-04-04","cited_by_count":5,"area":null},{"id":"2209.09593","title":"EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics","created":"2022-09-20","cited_by_count":4,"area":null},{"id":"2310.13998","title":"Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models","created":"2023-10-21","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":"2310.14001","title":"Toward Stronger Textual Attack Detectors","created":"2023-10-21","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":"2310.13990","title":"A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification","created":"2023-10-21","cited_by_count":1,"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":"2511.16478","title":"Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluation","created":"2025-11-20","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":"2205.15424","title":"Connecting adversarial attacks and optimal transport for domain adaptation","created":"2022-05-30","cited_by_count":0,"area":null},{"id":"2602.05419","title":"Grammatical Error Correction Evaluation by Optimally Transporting Edit Representation","created":"2026-02-05","cited_by_count":0,"area":null}],"next_cursor":null}