{"total":151,"rows":[{"id":"2302.14520","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","created":"2023-02-28","cited_by_count":420,"area":null},{"id":"2310.10482","title":"xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection","created":"2023-10-16","cited_by_count":265,"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":"2304.01852","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","created":"2023-04-04","cited_by_count":154,"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":"2211.09102","title":"Prompting PaLM for Translation: Assessing Strategies and Performance","created":"2022-11-16","cited_by_count":145,"area":null},{"id":"2308.07286","title":"The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation","created":"2023-08-14","cited_by_count":95,"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":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"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":"2212.08597","title":"Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better","created":"2022-12-16","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":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71,"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":"2406.11580","title":"Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation","created":"2024-06-17","cited_by_count":62,"area":null},{"id":"2208.05309","title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","created":"2022-08-10","cited_by_count":61,"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":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55,"area":null},{"id":"2212.09739","title":"LENS: A Learnable Evaluation Metric for Text Simplification","created":"2022-12-19","cited_by_count":54,"area":null},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54,"area":null},{"id":"2304.14317","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","created":"2023-04-27","cited_by_count":52,"area":null},{"id":"2206.11309","title":"GODEL: Large-Scale Pre-Training for Goal-Directed Dialog","created":"2022-06-22","cited_by_count":51,"area":null},{"id":"2205.00978","title":"Quality-Aware Decoding for Neural Machine Translation","created":"2022-05-02","cited_by_count":49,"area":null},{"id":"2405.00732","title":"LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report","created":"2024-04-29","cited_by_count":47,"area":null},{"id":"2305.04118","title":"Exploring Human-Like Translation Strategy with Large Language Models","created":"2023-05-06","cited_by_count":44,"area":null},{"id":"2305.13194","title":"SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation","created":"2023-05-22","cited_by_count":42,"area":null},{"id":"2202.05148","title":"Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET","created":"2022-02-10","cited_by_count":41,"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":"2402.16379","title":"TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement","created":"2024-02-26","cited_by_count":39,"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":"2305.01778","title":"SLTUNET: A Simple Unified Model for Sign Language Translation","created":"2023-05-02","cited_by_count":35,"area":null},{"id":"2306.16793","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","created":"2023-06-29","cited_by_count":29,"area":null},{"id":"2204.13346","title":"UniTE: Unified Translation Evaluation","created":"2022-04-28","cited_by_count":28,"area":null},{"id":"2312.13585","title":"Speech Translation with Large Language Models: An Industrial Practice","created":"2023-12-21","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":"2210.15615","title":"ACES: Translation Accuracy Challenge Sets for Evaluating Machine Translation Metrics","created":"2022-10-27","cited_by_count":25,"area":null},{"id":"2211.15464","title":"Considerations for meaningful sign language machine translation based on glosses","created":"2022-11-28","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":"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":"2305.08414","title":"What's the Meaning of Superhuman Performance in Today's NLU?","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2407.04910","title":"NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task","created":"2024-07-06","cited_by_count":23,"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":"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":"2208.01030","title":"SMART: Sentences as Basic Units for Text Evaluation","created":"2022-08-01","cited_by_count":18,"area":null},{"id":"2311.10174","title":"JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processing","created":"2023-11-16","cited_by_count":18,"area":null},{"id":"2212.08486","title":"BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric","created":"2022-12-16","cited_by_count":16,"area":null},{"id":"2109.02972","title":"Don't Go Far Off: An Empirical Study on Neural Poetry Translation","created":"2021-09-07","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":"2410.02381","title":"MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2110.07804","title":"Alternative Input Signals Ease Transfer in Multilingual Machine Translation","created":"2021-10-15","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":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2205.08533","title":"Consistent Human Evaluation of Machine Translation across Language Pairs","created":"2022-05-17","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":"2302.03788","title":"Toward a Theory of Causation for Interpreting Neural Code Models","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2304.13462","title":"Multidimensional Evaluation for Text Style Transfer Using ChatGPT","created":"2023-04-26","cited_by_count":12,"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":"2205.02293","title":"Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance","created":"2022-05-04","cited_by_count":11,"area":null},{"id":"2301.09008","title":"Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference","created":"2023-01-21","cited_by_count":11,"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":"2309.08832","title":"SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window","created":"2023-09-16","cited_by_count":11,"area":null},{"id":"2408.15366","title":"Pitfalls and Outlooks in Using COMET","created":"2024-08-27","cited_by_count":10,"area":null},{"id":"2410.10995","title":"Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation","created":"2024-10-14","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":"2511.18491","title":"MindEval: Benchmarking Language Models on Multi-turn Mental Health Support","created":"2025-11-23","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":"2205.09178","title":"PreQuEL: Quality Estimation of Machine Translation Outputs in Advance","created":"2022-05-18","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":"2312.13871","title":"Evaluating Task-oriented Dialogue Systems: A Systematic Review of Measures, Constructs and their Operationalisations","created":"2023-12-21","cited_by_count":9,"area":null},{"id":"2401.12097","title":"An Empirical Study of In-context Learning in LLMs for Machine Translation","created":"2024-01-22","cited_by_count":9,"area":null},{"id":"2402.15987","title":"Likelihood-based Mitigation of Evaluation Bias in Large Language Models","created":"2024-02-25","cited_by_count":9,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2303.15265","title":"Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation","created":"2023-03-27","cited_by_count":8,"area":null},{"id":"2404.19310","title":"Does Whisper understand Swiss German? An automatic, qualitative, and human evaluation","created":"2024-04-30","cited_by_count":8,"area":null},{"id":"2407.11855","title":"Scaling Sign Language Translation","created":"2024-07-16","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":"2109.10341","title":"Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents","created":"2021-09-21","cited_by_count":7,"area":null},{"id":"2205.11277","title":"When does Parameter-Efficient Transfer Learning Work for Machine Translation?","created":"2022-05-23","cited_by_count":7,"area":null},{"id":"2210.06990","title":"Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2401.01283","title":"Quality and Quantity of Machine Translation References for Automatic Metrics","created":"2024-01-02","cited_by_count":7,"area":null},{"id":"2402.07681","title":"Large Language Models \"Ad Referendum\": How Good Are They at Machine Translation in the Legal Domain?","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2110.09147","title":"BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation","created":"2021-10-18","cited_by_count":6,"area":null},{"id":"2402.19457","title":"$\\texttt{COSMIC}$: Mutual Information for Task-Agnostic Summarization Evaluation","created":"2024-02-29","cited_by_count":6,"area":null},{"id":"2406.07359","title":"GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2510.19367","title":"Sign Language Translation with Sentence Embedding Supervision","created":"2025-10-22","cited_by_count":6,"area":null},{"id":"2601.07338","title":"Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation","created":"2026-01-12","cited_by_count":6,"area":null},{"id":"2209.02962","title":"Adam Mickiewicz University at WMT 2022: NER-Assisted and Quality-Aware Neural Machine Translation","created":"2022-09-07","cited_by_count":5,"area":null},{"id":"2305.12786","title":"Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation","created":"2023-05-22","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":"2404.08259","title":"Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Study","created":"2024-04-12","cited_by_count":5,"area":null},{"id":"2406.14267","title":"On the Evaluation Practices in Multilingual NLP: Can Machine Translation Offer an Alternative to Human Translations?","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2410.14763","title":"Enabling Scalable Evaluation of Bias Patterns in Medical LLMs","created":"2024-10-18","cited_by_count":5,"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":"2503.05010","title":"Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2505.24456","title":"CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation","created":"2025-05-30","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}],"next_cursor":"100"}