{"list":"other","total":118,"rows":[{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2203.05794","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","created":"2022-03-11","cited_by_count":801},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2011.00620","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","created":"2020-11-01","cited_by_count":255},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218},{"id":"1610.08914","title":"Ex Machina: Personal Attacks Seen at Scale","created":"2016-10-27","cited_by_count":210},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177},{"id":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174},{"id":"2406.09948","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","created":"2024-06-14","cited_by_count":173},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146},{"id":"2012.15738","title":"Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences","created":"2020-12-31","cited_by_count":135},{"id":"2102.00894","title":"Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models","created":"2021-02-01","cited_by_count":132},{"id":"2006.06202","title":"A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages","created":"2020-06-11","cited_by_count":131},{"id":"2406.05967","title":"CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark","created":"2024-06-10","cited_by_count":120},{"id":"2010.06189","title":"X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models","created":"2020-10-13","cited_by_count":117},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109},{"id":"2407.10920","title":"Benchmarking Vision Language Models for Cultural Understanding","created":"2024-07-15","cited_by_count":101},{"id":"2205.12522","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","created":"2022-05-25","cited_by_count":100},{"id":"2404.15238","title":"CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies","created":"2024-04-23","cited_by_count":98},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93},{"id":"2402.11548","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","created":"2024-02-18","cited_by_count":91},{"id":"2210.07763","title":"Extracting Cultural Commonsense Knowledge at Scale","created":"2022-10-14","cited_by_count":76},{"id":"2307.16778","title":"KoBBQ: Korean Bias Benchmark for Question Answering","created":"2023-07-31","cited_by_count":71},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70},{"id":"2106.06937","title":"Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning","created":"2021-06-13","cited_by_count":65},{"id":"2011.03080","title":"EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering","created":"2020-11-05","cited_by_count":60},{"id":"2305.17008","title":"NormBank: A Knowledge Bank of Situational Social Norms","created":"2023-05-26","cited_by_count":60},{"id":"2404.16308","title":"WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models","created":"2024-04-25","cited_by_count":60},{"id":"2109.06860","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","created":"2021-09-14","cited_by_count":59},{"id":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53},{"id":"2310.04928","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","created":"2023-10-07","cited_by_count":53},{"id":"2104.04108","title":"XFORMAL: A Benchmark for Multilingual Formality Style Transfer","created":"2021-04-08","cited_by_count":52},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48},{"id":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47},{"id":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45},{"id":"2004.00798","title":"Mapping Languages: The Corpus of Global Language Use","created":"2020-04-02","cited_by_count":42},{"id":"2404.01854","title":"IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces","created":"2024-04-02","cited_by_count":39},{"id":"2108.05927","title":"Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languages","created":"2021-08-12","cited_by_count":38},{"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":"2212.10409","title":"ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations","created":"2022-12-20","cited_by_count":36},{"id":"2311.01012","title":"COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances","created":"2023-11-02","cited_by_count":35},{"id":"2405.17978","title":"FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model","created":"2024-05-28","cited_by_count":35},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35},{"id":"2310.18974","title":"EtiCor: Corpus for Analyzing LLMs for Etiquettes","created":"2023-10-29","cited_by_count":33},{"id":"2403.20147","title":"IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context","created":"2024-03-29","cited_by_count":32},{"id":"1904.11783","title":"Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors","created":"2019-04-26","cited_by_count":31},{"id":"2410.02677","title":"CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming","created":"2024-10-03","cited_by_count":30},{"id":"2310.16117","title":"NADI 2023: The Fourth Nuanced Arabic Dialect Identification Shared Task","created":"2023-10-24","cited_by_count":29},{"id":"2411.06032","title":"LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output","created":"2024-11-09","cited_by_count":27},{"id":"2508.01710","title":"CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications","created":"2025-08-03","cited_by_count":27},{"id":"2103.11528","title":"A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Texts","created":"2021-03-22","cited_by_count":25},{"id":"2205.04022","title":"CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality","created":"2022-05-09","cited_by_count":24},{"id":"2310.14563","title":"NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation","created":"2023-10-23","cited_by_count":24},{"id":"2402.18120","title":"Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?","created":"2024-02-28","cited_by_count":24},{"id":"2403.05696","title":"SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypes","created":"2024-03-08","cited_by_count":24},{"id":"2201.13405","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","created":"2022-01-31","cited_by_count":23},{"id":"2310.17586","title":"Global Voices, Local Biases: Socio-Cultural Prejudices across Languages","created":"2023-10-26","cited_by_count":23},{"id":"2311.16421","title":"CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models","created":"2023-11-28","cited_by_count":23},{"id":"2205.09501","title":"SDS-200: A Swiss German Speech to Standard German Text Corpus","created":"2022-05-19","cited_by_count":22},{"id":"2304.12026","title":"SocialDial: A Benchmark for Socially-Aware Dialogue Systems","created":"2023-04-24","cited_by_count":22},{"id":"2305.14492","title":"Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment","created":"2023-05-23","cited_by_count":22},{"id":"2501.04662","title":"On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena","created":"2025-01-08","cited_by_count":22},{"id":"2110.07385","title":"Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings","created":"2021-10-14","cited_by_count":21},{"id":"2011.01575","title":"AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings","created":"2020-11-03","cited_by_count":20},{"id":"2306.02475","title":"Modeling Cross-Cultural Pragmatic Inference with Codenames Duet","created":"2023-06-04","cited_by_count":20},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20},{"id":"2305.14839","title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","created":"2023-05-24","cited_by_count":19},{"id":"2411.03769","title":"No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages","created":"2024-11-06","cited_by_count":19},{"id":"2305.18855","title":"STT4SG-350: A Speech Corpus for All Swiss German Dialect Regions","created":"2023-05-30","cited_by_count":18},{"id":"2306.05076","title":"DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models","created":"2023-06-08","cited_by_count":17},{"id":"2303.08954","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","created":"2023-03-15","cited_by_count":16},{"id":"2307.14031","title":"Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems","created":"2023-07-26","cited_by_count":16},{"id":"2504.05154","title":"CARE: Multilingual Human Preference Learning for Cultural Awareness","created":"2025-04-07","cited_by_count":15},{"id":"2107.11584","title":"Extending Challenge Sets to Uncover Gender Bias in Machine Translation: Impact of Stereotypical Verbs and Adjectives","created":"2021-07-24","cited_by_count":14},{"id":"2210.01108","title":"SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis","created":"2022-10-03","cited_by_count":14},{"id":"2406.11622","title":"Building Knowledge-Guided Lexica to Model Cultural Variation","created":"2024-06-17","cited_by_count":11},{"id":"2103.01910","title":"MultiSubs: A Large-scale Multimodal and Multilingual Dataset","created":"2021-03-02","cited_by_count":10},{"id":"2505.18903","title":"StandUp4AI: A New Multilingual Dataset for Humor Detection in Stand-up Comedy Videos","created":"2025-05-24","cited_by_count":9},{"id":"2408.05102","title":"How Well Do LLMs Identify Cultural Unity in Diversity?","created":"2024-08-09","cited_by_count":8},{"id":"2503.17485","title":"SaudiCulture: A Benchmark for Evaluating Large Language Models Cultural Competence within Saudi Arabia","created":"2025-03-21","cited_by_count":8},{"id":"2506.19073","title":"MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanation","created":"2025-06-23","cited_by_count":8},{"id":"2011.08772","title":"KddRES: A Multi-level Knowledge-driven Dialogue Dataset for Restaurant Towards Customized Dialogue System","created":"2020-11-17","cited_by_count":7},{"id":"2106.03469","title":"Multilingual Neural Semantic Parsing for Low-Resourced Languages","created":"2021-06-07","cited_by_count":7}],"next_cursor":"100"}