{"total":887,"rows":[{"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":"2302.14520","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","created":"2023-02-28","cited_by_count":420,"area":null},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361,"area":null},{"id":"2104.14478","title":"Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation","created":"2021-04-29","cited_by_count":338,"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":"2301.07069","title":"Prompting Large Language Model for Machine Translation: A Case Study","created":"2023-01-17","cited_by_count":250,"area":null},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244,"area":null},{"id":"2209.06243","title":"CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task","created":"2022-09-13","cited_by_count":207,"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":"2212.02437","title":"In-context Examples Selection for Machine Translation","created":"2022-12-05","cited_by_count":172,"area":null},{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","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":"2304.04675","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","created":"2023-04-10","cited_by_count":160,"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":"2310.13988","title":"GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4","created":"2023-10-21","cited_by_count":146,"area":null},{"id":"2303.13780","title":"Towards Making the Most of ChatGPT for Machine Translation","created":"2023-03-24","cited_by_count":138,"area":null},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126,"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":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112,"area":null},{"id":"2406.15627","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","created":"2024-06-21","cited_by_count":105,"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":"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":"2203.15721","title":"On Decoding Strategies for Neural Text Generators","created":"2022-03-29","cited_by_count":90,"area":null},{"id":"2304.02210","title":"Document-Level Machine Translation with Large Language Models","created":"2023-04-05","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":"2305.15011","title":"Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation","created":"2023-05-24","cited_by_count":81,"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":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2307.07889","title":"LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models","created":"2023-07-15","cited_by_count":71,"area":null},{"id":"2310.00752","title":"TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks","created":"2023-10-01","cited_by_count":70,"area":null},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2308.04948","title":"Extrapolating Large Language Models to Non-English by Aligning Languages","created":"2023-08-09","cited_by_count":69,"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":"2204.09269","title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","created":"2022-04-20","cited_by_count":64,"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":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2210.14140","title":"Contrastive Search Is What You Need For Neural Text Generation","created":"2022-10-25","cited_by_count":59,"area":null},{"id":"2303.01911","title":"Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM","created":"2023-03-03","cited_by_count":59,"area":null},{"id":"2306.16842","title":"Tokenization and the Noiseless Channel","created":"2023-06-29","cited_by_count":59,"area":null},{"id":"2401.06468","title":"Adapting Large Language Models for Document-Level Machine Translation","created":"2024-01-12","cited_by_count":59,"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":"2401.12087","title":"Revisiting Demonstration Selection Strategies in In-Context Learning","created":"2024-01-22","cited_by_count":58,"area":null},{"id":"2404.13813","title":"From LLM to NMT: Advancing Low-Resource Machine Translation with Claude","created":"2024-04-22","cited_by_count":58,"area":null},{"id":"2105.08504","title":"Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation","created":"2021-05-18","cited_by_count":56,"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":"2305.14878","title":"Leveraging GPT-4 for Automatic Translation Post-Editing","created":"2023-05-24","cited_by_count":56,"area":null},{"id":"2308.14089","title":"MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records","created":"2023-08-27","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":"2305.14328","title":"Benchmarking Machine Translation with Cultural Awareness","created":"2023-05-23","cited_by_count":53,"area":null},{"id":"2309.13308","title":"Calibrating LLM-Based Evaluator","created":"2023-09-23","cited_by_count":53,"area":null},{"id":"2402.18191","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","created":"2024-02-28","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":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2305.11707","title":"What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability","created":"2023-05-19","cited_by_count":51,"area":null},{"id":"2310.01387","title":"It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk","created":"2023-10-02","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":"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":"2310.13448","title":"Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning","created":"2023-10-20","cited_by_count":49,"area":null},{"id":"2402.04177","title":"Scaling Laws for Downstream Task Performance of Large Language Models","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2105.03482","title":"Measuring and Increasing Context Usage in Context-Aware Machine Translation","created":"2021-05-07","cited_by_count":48,"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":"2407.05975","title":"LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages","created":"2024-07-08","cited_by_count":48,"area":null},{"id":"2104.08211","title":"Robust Open-Vocabulary Translation from Visual Text Representations","created":"2021-04-16","cited_by_count":47,"area":null},{"id":"2301.07779","title":"Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection","created":"2023-01-18","cited_by_count":44,"area":null},{"id":"2311.07978","title":"AfroBench: How Good are Large Language Models on African Languages?","created":"2023-11-14","cited_by_count":43,"area":null},{"id":"2406.03368","title":"IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models","created":"2024-06-05","cited_by_count":43,"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":"2108.12463","title":"Automatic Text Evaluation through the Lens of Wasserstein Barycenters","created":"2021-08-27","cited_by_count":38,"area":null},{"id":"2412.10271","title":"Benchmarking Linguistic Diversity of Large Language Models","created":"2024-12-13","cited_by_count":38,"area":null},{"id":"2502.02481","title":"Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study","created":"2025-02-04","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":"2401.11504","title":"With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation","created":"2024-01-21","cited_by_count":37,"area":null},{"id":"2109.07446","title":"When Does Translation Require Context? A Data-driven, Multilingual Exploration","created":"2021-09-15","cited_by_count":36,"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":"2402.12055","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria?","created":"2024-02-19","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":"2305.11746","title":"HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation","created":"2023-05-19","cited_by_count":35,"area":null},{"id":"2211.07733","title":"Speaking Multiple Languages Affects the Moral Bias of Language Models","created":"2022-11-14","cited_by_count":34,"area":null},{"id":"2304.02426","title":"ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback","created":"2023-04-05","cited_by_count":34,"area":null},{"id":"2311.14919","title":"Faster Minimum Bayes Risk Decoding with Confidence-based Pruning","created":"2023-11-25","cited_by_count":34,"area":null},{"id":"2309.10966","title":"MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods","created":"2023-09-19","cited_by_count":33,"area":null},{"id":"2311.08089","title":"Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment","created":"2023-11-14","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":"2304.14802","title":"ResiDual: Transformer with Dual Residual Connections","created":"2023-04-28","cited_by_count":31,"area":null},{"id":"2409.04599","title":"BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training","created":"2024-09-06","cited_by_count":31,"area":null},{"id":"2105.11921","title":"Focus Attention: Promoting Faithfulness and Diversity in Summarization","created":"2021-05-25","cited_by_count":30,"area":null},{"id":"2305.16806","title":"Do GPTs Produce Less Literal Translations?","created":"2023-05-26","cited_by_count":30,"area":null},{"id":"2405.12915","title":"G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation","created":"2024-05-21","cited_by_count":30,"area":null},{"id":"2502.04964","title":"Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistency","created":"2025-02-07","cited_by_count":30,"area":null},{"id":"2105.07476","title":"Data Augmentation for Sign Language Gloss Translation","created":"2021-05-16","cited_by_count":28,"area":null},{"id":"2204.13346","title":"UniTE: Unified Translation Evaluation","created":"2022-04-28","cited_by_count":28,"area":null}],"next_cursor":"100"}