{"total":143,"rows":[{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"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":"2310.13988","title":"GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4","created":"2023-10-21","cited_by_count":146,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2110.06341","title":"Learning Compact Metrics for MT","created":"2021-10-12","cited_by_count":93,"area":null},{"id":"2311.09766","title":"LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores","created":"2023-11-16","cited_by_count":90,"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":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"area":null},{"id":"2109.04650","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","created":"2021-09-10","cited_by_count":76,"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":"2305.14324","title":"Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration","created":"2023-05-23","cited_by_count":74,"area":null},{"id":"2106.15195","title":"Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers","created":"2021-06-29","cited_by_count":71,"area":null},{"id":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71,"area":null},{"id":"2208.03133","title":"Out of the BLEU: how should we assess quality of the Code Generation models?","created":"2022-08-05","cited_by_count":65,"area":null},{"id":"2105.08920","title":"OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics","created":"2021-05-19","cited_by_count":61,"area":null},{"id":"2109.06379","title":"Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation","created":"2021-09-14","cited_by_count":60,"area":null},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2109.05771","title":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2205.00978","title":"Quality-Aware Decoding for Neural Machine Translation","created":"2022-05-02","cited_by_count":49,"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":"2106.05555","title":"Shades of BLEU, Flavours of Success: The Case of MultiWOZ","created":"2021-06-10","cited_by_count":48,"area":null},{"id":"2401.06760","title":"Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies","created":"2024-01-12","cited_by_count":40,"area":null},{"id":"2204.10216","title":"Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metrics","created":"2022-04-21","cited_by_count":38,"area":null},{"id":"2210.13746","title":"DEMETR: Diagnosing Evaluation Metrics for Translation","created":"2022-10-25","cited_by_count":36,"area":null},{"id":"2211.07443","title":"Calibrated Interpretation: Confidence Estimation in Semantic Parsing","created":"2022-11-14","cited_by_count":33,"area":null},{"id":"2112.04139","title":"Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand","created":"2021-12-08","cited_by_count":32,"area":null},{"id":"2406.13439","title":"Finding Blind Spots in Evaluator LLMs with Interpretable Checklists","created":"2024-06-19","cited_by_count":32,"area":null},{"id":"2110.10746","title":"Better than Average: Paired Evaluation of NLP Systems","created":"2021-10-20","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":"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":"2204.09890","title":"Spurious Correlations in Reference-Free Evaluation of Text Generation","created":"2022-04-21","cited_by_count":26,"area":null},{"id":"2110.04399","title":"Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors","created":"2021-10-08","cited_by_count":25,"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":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24,"area":null},{"id":"2110.08329","title":"Control Prefixes for Parameter-Efficient Text Generation","created":"2021-10-15","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":"2310.19740","title":"Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks","created":"2023-10-30","cited_by_count":24,"area":null},{"id":"2109.14250","title":"BLEU, METEOR, BERTScore: Evaluation of Metrics Performance in Assessing Critical Translation Errors in Sentiment-oriented Text","created":"2021-09-29","cited_by_count":22,"area":null},{"id":"2405.20089","title":"The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities","created":"2024-05-30","cited_by_count":22,"area":null},{"id":"2409.14335","title":"MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators","created":"2024-09-22","cited_by_count":22,"area":null},{"id":"2106.06797","title":"Machine Translation into Low-resource Language Varieties","created":"2021-06-12","cited_by_count":19,"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":"2105.12437","title":"The statistical advantage of automatic NLG metrics at the system level","created":"2021-05-26","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":"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":"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":"2405.18348","title":"Can Automatic Metrics Assess High-Quality Translations?","created":"2024-05-28","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":"2305.11806","title":"The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics","created":"2023-05-19","cited_by_count":15,"area":null},{"id":"2410.04663","title":"Debate, Deliberate, Decide (D3): A Cost-Aware Adversarial Framework for Reliable and Interpretable LLM Evaluation","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2106.01478","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2210.16494","title":"Aligning Offline Metrics and Human Judgments of Value for Code Generation Models","created":"2022-10-29","cited_by_count":14,"area":null},{"id":"2212.10297","title":"Extrinsic Evaluation of Machine Translation Metrics","created":"2022-12-20","cited_by_count":14,"area":null},{"id":"2402.10422","title":"Pushing the Limits of Zero-shot End-to-End Speech Translation","created":"2024-02-16","cited_by_count":14,"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":"2504.00694","title":"On Benchmarking Code LLMs for Android Malware Analysis","created":"2025-04-01","cited_by_count":13,"area":null},{"id":"2104.07541","title":"Reward Optimization for Neural Machine Translation with Learned Metrics","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2304.05967","title":"Angler: Helping Machine Translation Practitioners Prioritize Model Improvements","created":"2023-04-12","cited_by_count":12,"area":null},{"id":"2112.08288","title":"Improving Both Domain Robustness and Domain Adaptability in Machine Translation","created":"2021-12-15","cited_by_count":11,"area":null},{"id":"2205.01966","title":"Non-Autoregressive Machine Translation: It's Not as Fast as it Seems","created":"2022-05-04","cited_by_count":11,"area":null},{"id":"2206.12514","title":"DetIE: Multilingual Open Information Extraction Inspired by Object Detection","created":"2022-06-24","cited_by_count":11,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2312.10610","title":"Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization","created":"2023-12-17","cited_by_count":10,"area":null},{"id":"2405.05376","title":"Krey\\`ol-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages","created":"2024-05-08","cited_by_count":10,"area":null},{"id":"2405.20529","title":"An Automatic Question Usability Evaluation Toolkit","created":"2024-05-30","cited_by_count":10,"area":null},{"id":"2410.05183","title":"Beyond Correlation: Interpretable Evaluation of Machine Translation Metrics","created":"2024-10-07","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":"2504.07583","title":"Do LLMs Understand Your Translations? Evaluating Paragraph-level MT with Question Answering","created":"2025-04-10","cited_by_count":10,"area":null},{"id":"2204.00004","title":"Reproducibility Issues for BERT-based Evaluation Metrics","created":"2022-03-30","cited_by_count":9,"area":null},{"id":"2204.13352","title":"RoBLEURT Submission for the WMT2021 Metrics Task","created":"2022-04-28","cited_by_count":9,"area":null},{"id":"2310.06707","title":"Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2103.16590","title":"Evaluating the Morphosyntactic Well-formedness of Generated Texts","created":"2021-03-30","cited_by_count":8,"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":"2305.06530","title":"How Good are Commercial Large Language Models on African Languages?","created":"2023-05-11","cited_by_count":8,"area":null},{"id":"2501.14883","title":"Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metrics","created":"2025-01-24","cited_by_count":8,"area":null},{"id":"2503.05931","title":"Training and Inference Efficiency of Encoder-Decoder Speech Models","created":"2025-03-07","cited_by_count":8,"area":null},{"id":"2105.13385","title":"Online Learning Meets Machine Translation Evaluation: Finding the Best Systems with the Least Human Effort","created":"2021-05-27","cited_by_count":7,"area":null},{"id":"2210.14486","title":"Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2310.07856","title":"Assessing Evaluation Metrics for Neural Test Oracle Generation","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2103.16789","title":"An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation","created":"2021-03-31","cited_by_count":6,"area":null},{"id":"2107.14402","title":"Difficulty-Aware Machine Translation Evaluation","created":"2021-07-30","cited_by_count":6,"area":null},{"id":"2303.07201","title":"An evaluation of Google Translate for Sanskrit to English translation via sentiment and semantic analysis","created":"2023-02-28","cited_by_count":6,"area":null},{"id":"2508.10175","title":"Estimating Machine Translation Difficulty","created":"2025-08-13","cited_by_count":6,"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":"2311.00508","title":"Robustness Tests for Automatic Machine Translation Metrics with Adversarial Attacks","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2403.04222","title":"Self-Evaluation of Large Language Model based on Glass-box Features","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2406.03881","title":"Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation","created":"2024-06-06","cited_by_count":5,"area":null},{"id":"2407.12832","title":"Sentence-level Aggregation of Lexical Metrics Correlates Stronger with Human Judgements than Corpus-level Aggregation","created":"2024-07-03","cited_by_count":5,"area":null},{"id":"2104.05700","title":"Macro-Average: Rare Types Are Important Too","created":"2021-04-12","cited_by_count":4,"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":"2209.07351","title":"Rethinking Round-Trip Translation for Machine Translation Evaluation","created":"2022-09-15","cited_by_count":4,"area":null},{"id":"2212.04205","title":"DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2410.16834","title":"Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2509.17349","title":"Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2201.06674","title":"TYPIC: A Corpus of Template-Based Diagnostic Comments on Argumentation","created":"2022-01-18","cited_by_count":3,"area":null},{"id":"2203.15858","title":"Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics","created":"2022-03-29","cited_by_count":3,"area":null},{"id":"2210.11612","title":"Searching for a higher power in the human evaluation of MT","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2306.03866","title":"Correction of Errors in Preference Ratings from Automated Metrics for Text Generation","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2403.02674","title":"Revisiting Meta-evaluation for Grammatical Error Correction","created":"2024-03-05","cited_by_count":3,"area":null}],"next_cursor":"100"}