{"total":106,"rows":[{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446,"area":null},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445,"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":"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":"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":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132,"area":null},{"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":"2205.12522","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","created":"2022-05-25","cited_by_count":100,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"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":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"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":"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":"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":"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":"2104.04108","title":"XFORMAL: A Benchmark for Multilingual Formality Style Transfer","created":"2021-04-08","cited_by_count":52,"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":"2401.07103","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","created":"2024-01-13","cited_by_count":37,"area":null},{"id":"2210.13746","title":"DEMETR: Diagnosing Evaluation Metrics for Translation","created":"2022-10-25","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":"2112.04139","title":"Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand","created":"2021-12-08","cited_by_count":32,"area":null},{"id":"2202.08479","title":"On the Evaluation Metrics for Paraphrase Generation","created":"2022-02-17","cited_by_count":32,"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":"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":"2306.03856","title":"Iterative Translation Refinement with Large Language Models","created":"2023-06-06","cited_by_count":27,"area":null},{"id":"2202.00528","title":"Examining Scaling and Transfer of Language Model Architectures for Machine Translation","created":"2022-02-01","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":"2110.08329","title":"Control Prefixes for Parameter-Efficient Text Generation","created":"2021-10-15","cited_by_count":24,"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":"2403.05303","title":"ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications","created":"2024-03-08","cited_by_count":20,"area":null},{"id":"2406.12419","title":"AI-Assisted Human Evaluation of Machine Translation","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2410.05193","title":"RevisEval: Improving LLM-as-a-Judge via Response-Adapted References","created":"2024-10-07","cited_by_count":20,"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":"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":"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":"2408.14622","title":"What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation","created":"2024-08-26","cited_by_count":17,"area":null},{"id":"2106.11388","title":"How well do you know your summarization datasets?","created":"2021-06-21","cited_by_count":16,"area":null},{"id":"2110.06997","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","created":"2021-10-13","cited_by_count":16,"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":"2305.11550","title":"Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens","created":"2023-05-19","cited_by_count":15,"area":null},{"id":"2212.07220","title":"Understanding Translationese in Cross-Lingual Summarization","created":"2022-12-14","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":"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":"2503.04554","title":"Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation","created":"2025-03-06","cited_by_count":14,"area":null},{"id":"2302.04907","title":"Binarized Neural Machine Translation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2406.02832","title":"Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms","created":"2024-06-05","cited_by_count":13,"area":null},{"id":"2103.17151","title":"Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models","created":"2021-03-31","cited_by_count":12,"area":null},{"id":"2106.03297","title":"On the Language Coverage Bias for Neural Machine Translation","created":"2021-06-07","cited_by_count":12,"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":"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":"2311.02851","title":"Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding","created":"2023-11-06","cited_by_count":10,"area":null},{"id":"2401.01419","title":"To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation","created":"2024-01-02","cited_by_count":10,"area":null},{"id":"2408.15366","title":"Pitfalls and Outlooks in Using COMET","created":"2024-08-27","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":"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":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","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":"2106.15880","title":"Mixed Cross Entropy Loss for Neural Machine Translation","created":"2021-06-30","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":"2108.08485","title":"Language Model Augmented Relevance Score","created":"2021-08-19","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":"2107.14402","title":"Difficulty-Aware Machine Translation Evaluation","created":"2021-07-30","cited_by_count":6,"area":null},{"id":"2210.09588","title":"Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2203.08394","title":"Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation","created":"2022-03-16","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":"2308.13170","title":"Measuring Spurious Correlation in Classification: 'Clever Hans' in Translationese","created":"2023-08-25","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":"2410.10867","title":"Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics","created":"2024-10-08","cited_by_count":5,"area":null},{"id":"2105.14488","title":"REAM$\\sharp$: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation","created":"2021-05-30","cited_by_count":4,"area":null},{"id":"2106.15818","title":"On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation","created":"2021-06-30","cited_by_count":4,"area":null},{"id":"2205.09273","title":"Twist Decoding: Diverse Generators Guide Each Other","created":"2022-05-19","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":"2501.17581","title":"CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2111.04079","title":"Variance-Aware Machine Translation Test Sets","created":"2021-11-07","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":"2401.05072","title":"Aligning Translation-Specific Understanding to General Understanding in Large Language Models","created":"2024-01-10","cited_by_count":3,"area":null},{"id":"2403.12242","title":"Reference-based Metrics Disprove Themselves in Question Generation","created":"2024-03-18","cited_by_count":3,"area":null},{"id":"2608.25089","title":"Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation","created":"2026-08-25","cited_by_count":3,"area":null},{"id":"2211.13865","title":"Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?","created":"2022-11-25","cited_by_count":2,"area":null},{"id":"2306.05077","title":"Improving Language Model Integration for Neural Machine Translation","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2308.08982","title":"Evaluation of really good grammatical error correction","created":"2023-08-17","cited_by_count":2,"area":null},{"id":"2406.01131","title":"Favi-Score: A Measure for Favoritism in Automated Preference Ratings for Generative AI Evaluation","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2505.20264","title":"We Need to Measure Data Diversity in NLP -- Better and Broader","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2601.10580","title":"Form and Meaning in Intrinsic Multilingual Evaluations","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2206.02737","title":"Investigating the use of Paraphrase Generation for Question Reformulation in the FRANK QA system","created":"2022-06-06","cited_by_count":1,"area":null},{"id":"2211.04126","title":"Conciseness: An Overlooked Language Task","created":"2022-11-08","cited_by_count":1,"area":null},{"id":"2305.12918","title":"Improving Metrics for Speech Translation","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2407.12196","title":"MASIVE: Open-Ended Affective State Identification in English and Spanish","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2502.08561","title":"Quality-Aware Decoding: Unifying Quality Estimation and Decoding","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2505.24472","title":"VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2606.10657","title":"Are We Evaluating Knowledge or Phrasing? Mitigating MCQA Sensitivity with ParaEval","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2608.03803","title":"M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2205.11826","title":"Lack of Fluency is Hurting Your Translation Model","created":"2022-05-24","cited_by_count":0,"area":null},{"id":"2312.00536","title":"Trained MT Metrics Learn to Cope with Machine-translated References","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2510.06242","title":"Transparent Reference-free Automated Evaluation of Open-Ended User Survey Responses","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2512.15556","title":"An Empirical Study on Chinese Character Decomposition in Multiword Expression-Aware Neural Machine Translation","created":"2025-12-17","cited_by_count":0,"area":null}],"next_cursor":"100"}