{"total":63,"rows":[{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117,"area":null},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102,"area":null},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"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":"2206.09755","title":"Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold","created":"2022-06-20","cited_by_count":29,"area":null},{"id":"2202.03086","title":"Machine Translation from Signed to Spoken Languages: State of the Art and Challenges","created":"2022-02-07","cited_by_count":20,"area":null},{"id":"2410.15956","title":"Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs","created":"2024-10-21","cited_by_count":19,"area":null},{"id":"2204.02292","title":"Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval","created":"2022-04-05","cited_by_count":17,"area":null},{"id":"2405.06346","title":"Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology","created":"2024-05-10","cited_by_count":17,"area":null},{"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,"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":"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,"area":null},{"id":"2306.17674","title":"X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents","created":"2023-06-30","cited_by_count":13,"area":null},{"id":"2407.05740","title":"Do Multilingual Large Language Models Mitigate Stereotype Bias?","created":"2024-07-08","cited_by_count":13,"area":null},{"id":"2210.12929","title":"Finding Memo: Extractive Memorization in Constrained Sequence Generation Tasks","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2409.12958","title":"MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions","created":"2024-09-19","cited_by_count":12,"area":null},{"id":"2107.05987","title":"Generating Gender Augmented Data for NLP","created":"2021-07-13","cited_by_count":11,"area":null},{"id":"2407.18454","title":"Fairness Definitions in Language Models Explained","created":"2024-07-26","cited_by_count":11,"area":null},{"id":"2304.11501","title":"Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation","created":"2023-04-23","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":"2409.12623","title":"CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks","created":"2024-09-19","cited_by_count":10,"area":null},{"id":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2510.03136","title":"Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models","created":"2025-10-03","cited_by_count":10,"area":null},{"id":"2502.11020","title":"TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages","created":"2025-02-16","cited_by_count":9,"area":null},{"id":"2208.00318","title":"Smoothing Entailment Graphs with Language Models","created":"2022-07-30","cited_by_count":8,"area":null},{"id":"2307.13405","title":"Towards Bridging the Digital Language Divide","created":"2023-07-25","cited_by_count":7,"area":null},{"id":"2505.08546","title":"Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translation","created":"2025-05-13","cited_by_count":7,"area":null},{"id":"2306.11420","title":"On Evaluating Multilingual Compositional Generalization with Translated Datasets","created":"2023-06-20","cited_by_count":6,"area":null},{"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,"area":null},{"id":"2405.20512","title":"How Multilingual Are Large Language Models Fine-Tuned for Translation?","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2406.10882","title":"SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models","created":"2024-06-16","cited_by_count":6,"area":null},{"id":"2408.17308","title":"Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation","created":"2024-08-30","cited_by_count":5,"area":null},{"id":"2105.04616","title":"Automatic Classification of Human Translation and Machine Translation: A Study from the Perspective of Lexical Diversity","created":"2021-05-10","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":"2307.13714","title":"Diversity and Language Technology: How Techno-Linguistic Bias Can Cause Epistemic Injustice","created":"2023-07-25","cited_by_count":4,"area":null},{"id":"2401.10016","title":"Gender Bias in Machine Translation and The Era of Large Language Models","created":"2024-01-18","cited_by_count":4,"area":null},{"id":"2503.24013","title":"You Cannot Feed Two Birds with One Score: the Accuracy-Naturalness Tradeoff in Translation","created":"2025-03-31","cited_by_count":4,"area":null},{"id":"2509.21294","title":"UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2305.12737","title":"The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2109.12105","title":"Faithful Target Attribute Prediction in Neural Machine Translation","created":"2021-09-24","cited_by_count":2,"area":null},{"id":"2210.06709","title":"Categorizing Semantic Representations for Neural Machine Translation","created":"2022-10-13","cited_by_count":2,"area":null},{"id":"2407.10152","title":"Mitigating Translationese in Low-resource Languages: The Storyboard Approach","created":"2024-07-14","cited_by_count":2,"area":null},{"id":"2407.11186","title":"Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2506.22050","title":"Decoding Machine Translationese in English-Chinese News: LLMs vs. NMTs","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2109.08129","title":"Does Summary Evaluation Survive Translation to Other Languages?","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2311.06204","title":"BanglaBait: Semi-Supervised Adversarial Approach for Clickbait Detection on Bangla Clickbait Dataset","created":"2023-11-10","cited_by_count":1,"area":null},{"id":"2404.08661","title":"The Comparison of Translationese in Machine Translation and Human Transation in terms of Translation Relations","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2404.19254","title":"Suvach -- Generated Hindi QA benchmark","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2410.21126","title":"Current State-of-the-Art of Bias Detection and Mitigation in Machine Translation for African and European Languages: a Review","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2504.14105","title":"Amplify Initiative: Building A Localized Data Platform for Globalized AI","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2507.03933","title":"Losing our Tail, Again: (Un)Natural Selection & Multilingual LLMs","created":"2025-07-05","cited_by_count":1,"area":null},{"id":"2507.22159","title":"IndoPref: A Multi-Domain Pairwise Preference Dataset for Indonesian","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2609.08779","title":"Improving Term Evaluation in Machine Translation: Variation Matters","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2409.09568","title":"Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing?","created":"2024-09-15","cited_by_count":0,"area":null},{"id":"2511.01360","title":"Safer in Translation? Presupposition Robustness in Indic Languages","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2601.17764","title":"Cross-Lingual Probing and Community-Grounded Analysis of Gender Bias in Low-Resource Bengali","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2602.16469","title":"Dialects of Translationese Shape Language Model Learning","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.08450","title":"A Dataset for Probing Translationese Preferences in English-to-Swedish Translation","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2605.07622","title":"Is She Even Relevant? When BERT Ignores Explicit Gender Cues","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.10113","title":"Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.00890","title":"MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.17173","title":"KyrgyzLLM-Bench: Benchmarking Kyrgyz Language Understanding","created":"2026-07-19","cited_by_count":0,"area":null}],"next_cursor":null}