{"list":"other","total":63,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2309.03882","title":"Large Language Models Are Not Robust Multiple Choice Selectors","created":"2023-09-07","cited_by_count":486},{"id":"2302.14520","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","created":"2023-02-28","cited_by_count":420},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"1903.10561","title":"On Measuring Social Biases in Sentence Encoders","created":"2019-03-25","cited_by_count":398},{"id":"2310.10482","title":"xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection","created":"2023-10-16","cited_by_count":265},{"id":"1906.00591","title":"Evaluating Gender Bias in Machine Translation","created":"2019-06-03","cited_by_count":249},{"id":"2209.06243","title":"CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task","created":"2022-09-13","cited_by_count":207},{"id":"2402.17733","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","created":"2024-02-27","cited_by_count":206},{"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},{"id":"2310.13988","title":"GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4","created":"2023-10-21","cited_by_count":146},{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117},{"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},{"id":"1909.05088","title":"Getting Gender Right in Neural Machine Translation","created":"2019-09-11","cited_by_count":98},{"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},{"id":"2309.11925","title":"Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task","created":"2023-09-21","cited_by_count":88},{"id":"2004.04498","title":"Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem","created":"2020-04-09","cited_by_count":86},{"id":"2106.14574","title":"Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics","created":"2021-06-28","cited_by_count":83},{"id":"2305.14324","title":"Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration","created":"2023-05-23","cited_by_count":74},{"id":"1901.04562","title":"Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements","created":"2019-01-14","cited_by_count":70},{"id":"1901.03116","title":"Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques","created":"2019-01-10","cited_by_count":65},{"id":"2109.03858","title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation","created":"2021-09-08","cited_by_count":62},{"id":"1905.11684","title":"On Measuring Gender Bias in Translation of Gender-neutral Pronouns","created":"2019-05-28","cited_by_count":60},{"id":"2103.11878","title":"BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation","created":"2021-03-22","cited_by_count":58},{"id":"2010.15535","title":"Unbabel's Participation in the WMT20 Metrics Shared Task","created":"2020-10-29","cited_by_count":56},{"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},{"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},{"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},{"id":"2010.05332","title":"Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It","created":"2020-10-11","cited_by_count":40},{"id":"2211.01355","title":"MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation","created":"2022-11-02","cited_by_count":38},{"id":"2401.12873","title":"Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model","created":"2024-01-23","cited_by_count":33},{"id":"2306.04597","title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","created":"2023-06-07","cited_by_count":28},{"id":"2402.17954","title":"Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps","created":"2024-02-28","cited_by_count":25},{"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},{"id":"2305.14711","title":"Gender Biases in Automatic Evaluation Metrics for Image Captioning","created":"2023-05-24","cited_by_count":24},{"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},{"id":"1911.03642","title":"Towards Understanding Gender Bias in Relation Extraction","created":"2019-11-09","cited_by_count":23},{"id":"2402.18747","title":"Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains","created":"2024-02-28","cited_by_count":21},{"id":"2310.05294","title":"Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with the GeNTE Corpus","created":"2023-10-08","cited_by_count":20},{"id":"2305.16051","title":"What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns","created":"2023-05-25","cited_by_count":19},{"id":"2310.12127","title":"A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation","created":"2023-10-18","cited_by_count":19},{"id":"2311.05350","title":"There's no Data Like Better Data: Using QE Metrics for MT Data Filtering","created":"2023-11-09","cited_by_count":19},{"id":"2311.09132","title":"Aligning Neural Machine Translation Models: Human Feedback in Training and Inference","created":"2023-11-15","cited_by_count":19},{"id":"2303.03975","title":"GATE: A Challenge Set for Gender-Ambiguous Translation Examples","created":"2023-03-07","cited_by_count":18},{"id":"2108.02854","title":"GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena","created":"2021-08-05","cited_by_count":16},{"id":"2310.11430","title":"An Empirical Study of Translation Hypothesis Ensembling with Large Language Models","created":"2023-10-17","cited_by_count":16},{"id":"2405.18348","title":"Can Automatic Metrics Assess High-Quality Translations?","created":"2024-05-28","cited_by_count":16},{"id":"2410.00545","title":"What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study","created":"2024-10-01","cited_by_count":15},{"id":"2401.06688","title":"Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation","created":"2024-01-12","cited_by_count":13},{"id":"2407.18786","title":"The power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs","created":"2024-07-26","cited_by_count":12},{"id":"2305.14016","title":"Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation","created":"2023-05-23","cited_by_count":10},{"id":"2405.08477","title":"Enhancing Gender-Inclusive Machine Translation with Neomorphemes and Large Language Models","created":"2024-05-14","cited_by_count":7},{"id":"2401.04972","title":"Whose wife is it anyway? Assessing bias against same-gender relationships in machine translation","created":"2024-01-10","cited_by_count":6},{"id":"2403.08314","title":"Is Context Helpful for Chat Translation Evaluation?","created":"2024-03-13","cited_by_count":5},{"id":"2210.08859","title":"Social Biases in Automatic Evaluation Metrics for NLG","created":"2022-10-17","cited_by_count":3},{"id":"2407.20438","title":"Generating Gender Alternatives in Machine Translation","created":"2024-07-29","cited_by_count":3}],"next_cursor":null}