{"total":25,"rows":[{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111,"area":null},{"id":"2111.09388","title":"High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics","created":"2021-11-17","cited_by_count":104,"area":null},{"id":"2110.06341","title":"Learning Compact Metrics for MT","created":"2021-10-12","cited_by_count":93,"area":null},{"id":"2202.07654","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2305.09860","title":"Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation","created":"2023-05-17","cited_by_count":58,"area":null},{"id":"2211.07634","title":"Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding","created":"2022-11-14","cited_by_count":54,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2204.13346","title":"UniTE: Unified Translation Evaluation","created":"2022-04-28","cited_by_count":28,"area":null},{"id":"2210.15615","title":"ACES: Translation Accuracy Challenge Sets for Evaluating Machine Translation Metrics","created":"2022-10-27","cited_by_count":25,"area":null},{"id":"2305.14282","title":"INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback","created":"2023-05-23","cited_by_count":22,"area":null},{"id":"2111.06467","title":"SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets","created":"2021-11-11","cited_by_count":18,"area":null},{"id":"2401.16313","title":"Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets","created":"2024-01-29","cited_by_count":18,"area":null},{"id":"2411.03524","title":"Mitigating Metric Bias in Minimum Bayes Risk Decoding","created":"2024-11-05","cited_by_count":16,"area":null},{"id":"2302.00944","title":"TransFool: An Adversarial Attack against Neural Machine Translation Models","created":"2023-02-02","cited_by_count":12,"area":null},{"id":"2506.19571","title":"Has Machine Translation Evaluation Achieved Human Parity? The Human Reference and the Limits of Progress","created":"2025-06-24","cited_by_count":10,"area":null},{"id":"2204.06546","title":"Disentangling Uncertainty in Machine Translation Evaluation","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2109.14895","title":"Sentiment-Aware Measure (SAM) for Evaluating Sentiment Transfer by Machine Translation Systems","created":"2021-09-30","cited_by_count":4,"area":null},{"id":"2308.15246","title":"A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2303.00242","title":"DIFFQG: Generating Questions to Summarize Factual Changes","created":"2023-03-01","cited_by_count":3,"area":null},{"id":"2311.01153","title":"ACES: Translation Accuracy Challenge Sets at WMT 2023","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2302.03491","title":"Learning Translation Quality Evaluation on Low Resource Languages from Large Language Models","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2302.14785","title":"Joint Representations of Text and Knowledge Graphs for Retrieval and Evaluation","created":"2023-02-28","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":"2601.09725","title":"Assessing and Improving Punctuation Robustness in English-Marathi Machine Translation","created":"2025-12-28","cited_by_count":0,"area":null}],"next_cursor":null}