{"total":115,"rows":[{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282,"area":null},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722,"area":null},{"id":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422,"area":null},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361,"area":null},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2212.07919","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","created":"2022-12-15","cited_by_count":177,"area":"lr"},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175,"area":"safety"},{"id":"2212.02437","title":"In-context Examples Selection for Machine Translation","created":"2022-12-05","cited_by_count":172,"area":null},{"id":"2107.10821","title":"To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation","created":"2021-07-22","cited_by_count":163,"area":null},{"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":"2110.06341","title":"Learning Compact Metrics for MT","created":"2021-10-12","cited_by_count":93,"area":null},{"id":"2410.03983","title":"MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task","created":"2024-10-04","cited_by_count":93,"area":null},{"id":"2303.13809","title":"Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models","created":"2023-03-24","cited_by_count":87,"area":null},{"id":"2304.00723","title":"Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Study","created":"2023-04-03","cited_by_count":85,"area":null},{"id":"2304.10703","title":"ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness","created":"2023-04-21","cited_by_count":77,"area":"lr"},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2209.13654","title":"Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metric","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2309.13308","title":"Calibrating LLM-Based Evaluator","created":"2023-09-23","cited_by_count":53,"area":null},{"id":"2210.12563","title":"On the Limitations of Reference-Free Evaluations of Generated Text","created":"2022-10-22","cited_by_count":52,"area":null},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2210.07626","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation","created":"2022-10-14","cited_by_count":48,"area":null},{"id":"2210.14250","title":"Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature","created":"2022-10-25","cited_by_count":45,"area":null},{"id":"2108.12463","title":"Automatic Text Evaluation through the Lens of Wasserstein Barycenters","created":"2021-08-27","cited_by_count":38,"area":null},{"id":"2401.07103","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","created":"2024-01-13","cited_by_count":37,"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":"2210.13746","title":"DEMETR: Diagnosing Evaluation Metrics for Translation","created":"2022-10-25","cited_by_count":36,"area":null},{"id":"2410.03115","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","created":"2024-10-04","cited_by_count":36,"area":null},{"id":"2109.06352","title":"Uncertainty-Aware Machine Translation Evaluation","created":"2021-09-13","cited_by_count":35,"area":null},{"id":"2401.05749","title":"A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism","created":"2024-01-11","cited_by_count":35,"area":null},{"id":"2402.15754","title":"HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition","created":"2024-02-24","cited_by_count":33,"area":"alignment"},{"id":"2112.04139","title":"Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand","created":"2021-12-08","cited_by_count":32,"area":null},{"id":"2104.06457","title":"Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation","created":"2021-04-13","cited_by_count":28,"area":"distill"},{"id":"2204.13346","title":"UniTE: Unified Translation Evaluation","created":"2022-04-28","cited_by_count":28,"area":null},{"id":"2212.10180","title":"IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages","created":"2022-12-20","cited_by_count":27,"area":null},{"id":"2409.09598","title":"Improving Statistical Significance in Human Evaluation of Automatic Metrics via Soft Pairwise Accuracy","created":"2024-09-15","cited_by_count":25,"area":null},{"id":"2305.14711","title":"Gender Biases in Automatic Evaluation Metrics for Image Captioning","created":"2023-05-24","cited_by_count":24,"area":null},{"id":"2307.03131","title":"BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training","created":"2023-07-06","cited_by_count":24,"area":null},{"id":"2310.19792","title":"The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metrics","created":"2023-10-30","cited_by_count":23,"area":null},{"id":"2411.02429","title":"IdeaBench: Benchmarking Large Language Models for Research Idea Generation","created":"2024-10-31","cited_by_count":23,"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":"2402.18747","title":"Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains","created":"2024-02-28","cited_by_count":21,"area":null},{"id":"2408.13831","title":"Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In!","created":"2024-08-25","cited_by_count":21,"area":null},{"id":"2212.05726","title":"T5Score: Discriminative Fine-tuning of Generative Evaluation Metrics","created":"2022-12-12","cited_by_count":19,"area":null},{"id":"2208.01030","title":"SMART: Sentences as Basic Units for Text Evaluation","created":"2022-08-01","cited_by_count":18,"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":"2210.05035","title":"Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis","created":"2022-10-10","cited_by_count":18,"area":null},{"id":"2212.10179","title":"Toward Human-Like Evaluation for Natural Language Generation with Error Analysis","created":"2022-12-20","cited_by_count":18,"area":null},{"id":"2211.01482","title":"RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question","created":"2022-11-02","cited_by_count":17,"area":null},{"id":"2212.12137","title":"Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing","created":"2022-12-23","cited_by_count":17,"area":null},{"id":"2109.06798","title":"Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction","created":"2021-09-14","cited_by_count":16,"area":null},{"id":"2401.06568","title":"Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation","created":"2024-01-12","cited_by_count":16,"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":"2306.13041","title":"Towards Explainable Evaluation Metrics for Machine Translation","created":"2023-06-22","cited_by_count":15,"area":null},{"id":"2501.03545","title":"Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation","created":"2025-01-07","cited_by_count":15,"area":null},{"id":"2211.00922","title":"Dialect-robust Evaluation of Generated Text","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2212.10548","title":"T-Projection: High Quality Annotation Projection for Sequence Labeling Tasks","created":"2022-12-20","cited_by_count":14,"area":null},{"id":"2401.17099","title":"MT-Ranker: Reference-free machine translation evaluation by inter-system ranking","created":"2024-01-30","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":"2401.06688","title":"Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation","created":"2024-01-12","cited_by_count":13,"area":null},{"id":"2303.13989","title":"Paraphrase Detection: Human vs. Machine Content","created":"2023-03-24","cited_by_count":12,"area":null},{"id":"2305.15067","title":"Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2103.12777","title":"Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning","created":"2021-03-23","cited_by_count":10,"area":null},{"id":"2412.17592","title":"Investigating Length Issues in Document-level Machine Translation","created":"2024-12-23","cited_by_count":10,"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":"2212.09305","title":"SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2303.08991","title":"DeltaScore: Fine-Grained Story Evaluation with Perturbations","created":"2023-03-15","cited_by_count":9,"area":null},{"id":"2308.13506","title":"Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level","created":"2023-08-25","cited_by_count":9,"area":null},{"id":"2410.09644","title":"Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?","created":"2024-10-12","cited_by_count":9,"area":null},{"id":"2501.12011","title":"Reference-free Evaluation Metrics for Text Generation: A Survey","created":"2025-01-21","cited_by_count":9,"area":null},{"id":"2104.05146","title":"Assessing Reference-Free Peer Evaluation for Machine Translation","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2210.03235","title":"Improving Large-scale Paraphrase Acquisition and Generation","created":"2022-10-06","cited_by_count":8,"area":null},{"id":"2409.12060","title":"PARAPHRASUS : A Comprehensive Benchmark for Evaluating Paraphrase Detection Models","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2109.07242","title":"Regressive Ensemble for Machine Translation Quality Evaluation","created":"2021-09-15","cited_by_count":6,"area":null},{"id":"2109.14150","title":"Improving Arabic Diacritization by Learning to Diacritize and Translate","created":"2021-09-29","cited_by_count":6,"area":null},{"id":"2204.13692","title":"NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures","created":"2022-04-28","cited_by_count":6,"area":null},{"id":"2205.04651","title":"ParaCotta: Synthetic Multilingual Paraphrase Corpora from the Most Diverse Translation Sample Pair","created":"2022-05-10","cited_by_count":6,"area":null},{"id":"2211.12118","title":"HaRiM$^+$: Evaluating Summary Quality with Hallucination Risk","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2308.04386","title":"Learning Evaluation Models from Large Language Models for Sequence Generation","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2503.03044","title":"QE4PE: Word-level Quality Estimation for Human Post-Editing","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2203.04507","title":"Onception: Active Learning with Expert Advice for Real World Machine Translation","created":"2022-03-09","cited_by_count":5,"area":null},{"id":"2305.19330","title":"Breeding Machine Translations: Evolutionary approach to survive and thrive in the world of automated evaluation","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2107.08251","title":"Generative Pretraining for Paraphrase Evaluation","created":"2021-07-17","cited_by_count":4,"area":null},{"id":"2304.11065","title":"Conversational Process Modeling: Can Generative AI Empower Domain Experts in Creating and Redesigning Process Models?","created":"2023-04-19","cited_by_count":4,"area":null},{"id":"2305.13309","title":"Evaluating Factual Consistency of Texts with Semantic Role Labeling","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2305.14757","title":"Psychological Metrics for Dialog System Evaluation","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2502.11115","title":"Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2109.05611","title":"Levenshtein Training for Word-level Quality Estimation","created":"2021-09-12","cited_by_count":3,"area":null},{"id":"2205.12394","title":"MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification","created":"2022-05-24","cited_by_count":3,"area":null},{"id":"2305.13204","title":"Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2401.06769","title":"Machine Translation Models are Zero-Shot Detectors of Translation Direction","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2403.17640","title":"REFeREE: A REference-FREE Model-Based Metric for Text Simplification","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2406.08092","title":"Languages Transferred Within the Encoder: On Representation Transfer in Zero-Shot Multilingual Translation","created":"2024-06-12","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":"2208.01307","title":"Multilingual Coreference Resolution in Multiparty Dialogue","created":"2022-08-02","cited_by_count":2,"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":"2309.04725","title":"EPA: Easy Prompt Augmentation on Large Language Models via Multiple Sources and Multiple Targets","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2309.10066","title":"Automatic Personalized Impression Generation for PET Reports Using Large Language Models","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2412.03152","title":"A Measure of the System Dependence of Automated Metrics","created":"2024-12-04","cited_by_count":2,"area":null}],"next_cursor":"100"}