{"total":178,"rows":[{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311,"area":null},{"id":"2303.17466","title":"Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study","created":"2023-03-30","cited_by_count":206,"area":null},{"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,"area":null},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149,"area":null},{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139,"area":null},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68,"area":null},{"id":"2305.11840","title":"SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models","created":"2023-05-19","cited_by_count":66,"area":null},{"id":"2402.09369","title":"Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking","created":"2024-02-14","cited_by_count":63,"area":null},{"id":"2409.11360","title":"AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances","created":"2024-09-17","cited_by_count":60,"area":null},{"id":"2305.14328","title":"Benchmarking Machine Translation with Cultural Awareness","created":"2023-05-23","cited_by_count":53,"area":null},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49,"area":null},{"id":"2305.16171","title":"Multi-lingual and Multi-cultural Figurative Language Understanding","created":"2023-05-25","cited_by_count":47,"area":null},{"id":"2502.12057","title":"Culture is Not Trivia: Sociocultural Theory for Cultural NLP","created":"2025-02-17","cited_by_count":40,"area":null},{"id":"2408.06929","title":"Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas","created":"2024-08-13","cited_by_count":37,"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":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31,"area":null},{"id":"2407.06863","title":"Beyond Aesthetics: Cultural Competence in Text-to-Image Models","created":"2024-07-09","cited_by_count":30,"area":null},{"id":"2410.02677","title":"CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming","created":"2024-10-03","cited_by_count":30,"area":null},{"id":"2305.19474","title":"Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers","created":"2023-05-31","cited_by_count":27,"area":null},{"id":"2502.11926","title":"BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages","created":"2025-02-17","cited_by_count":27,"area":null},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2502.08045","title":"Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs","created":"2025-02-12","cited_by_count":26,"area":null},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2305.08414","title":"What's the Meaning of Superhuman Performance in Today's NLU?","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22,"area":null},{"id":"2211.13069","title":"Cultural Incongruencies in Artificial Intelligence","created":"2022-11-19","cited_by_count":21,"area":null},{"id":"2303.17927","title":"Cross-Cultural Transfer Learning for Chinese Offensive Language Detection","created":"2023-03-31","cited_by_count":21,"area":null},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"area":null},{"id":"2306.02475","title":"Modeling Cross-Cultural Pragmatic Inference with Codenames Duet","created":"2023-06-04","cited_by_count":20,"area":null},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2502.14301","title":"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models","created":"2025-02-20","cited_by_count":19,"area":null},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2310.06458","title":"Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features","created":"2023-10-10","cited_by_count":18,"area":null},{"id":"2401.10352","title":"Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys","created":"2024-01-18","cited_by_count":18,"area":null},{"id":"2402.18045","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","created":"2024-02-28","cited_by_count":18,"area":null},{"id":"2302.12578","title":"Fairness in Language Models Beyond English: Gaps and Challenges","created":"2023-02-24","cited_by_count":16,"area":null},{"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,"area":null},{"id":"2401.10535","title":"The \"Colonial Impulse\" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases","created":"2024-01-19","cited_by_count":16,"area":null},{"id":"2405.13974","title":"CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models","created":"2024-05-22","cited_by_count":16,"area":null},{"id":"2406.14504","title":"Translating Across Cultures: LLMs for Intralingual Cultural Adaptation","created":"2024-06-20","cited_by_count":16,"area":null},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2506.08835","title":"CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics","created":"2025-06-10","cited_by_count":15,"area":null},{"id":"2206.01134","title":"Language and Culture Internalisation for Human-Like Autotelic AI","created":"2022-06-02","cited_by_count":14,"area":null},{"id":"2502.14906","title":"Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2510.05931","title":"Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2310.15383","title":"GD-COMET: A Geo-Diverse Commonsense Inference Model","created":"2023-10-23","cited_by_count":13,"area":null},{"id":"2405.02411","title":"The Call for Socially Aware Language Technologies","created":"2024-05-03","cited_by_count":13,"area":null},{"id":"2409.07388","title":"Recent Advances in Multimodal Affective Computing: An NLP Perspective","created":"2024-09-11","cited_by_count":13,"area":null},{"id":"2603.06865","title":"Counting on Consensus: Selecting the Right Inter-annotator Agreement Metric for NLP Annotation and Evaluation","created":"2026-03-06","cited_by_count":13,"area":null},{"id":"2306.00639","title":"Being Right for Whose Right Reasons?","created":"2023-06-01","cited_by_count":12,"area":null},{"id":"2407.05022","title":"A Principled Framework for Evaluating on Typologically Diverse Languages","created":"2024-07-06","cited_by_count":12,"area":null},{"id":"2410.15453","title":"CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts","created":"2024-10-20","cited_by_count":11,"area":null},{"id":"2405.12744","title":"The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuning","created":"2024-05-21","cited_by_count":10,"area":null},{"id":"2502.19190","title":"Provocations from the Humanities for Generative AI Research","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2505.21548","title":"Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2310.19567","title":"CreoleVal: Multilingual Multitask Benchmarks for Creoles","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2410.16451","title":"Susu Box or Piggy Bank: Assessing Cultural Commonsense Knowledge between Ghana and the U.S","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2503.07269","title":"SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2210.04600","title":"YFACC: A Yor\\`ub\\'a speech-image dataset for cross-lingual keyword localisation through visual grounding","created":"2022-10-10","cited_by_count":8,"area":null},{"id":"2311.07897","title":"CPopQA: Ranking Cultural Concept Popularity by LLMs","created":"2023-11-14","cited_by_count":8,"area":null},{"id":"2408.05102","title":"How Well Do LLMs Identify Cultural Unity in Diversity?","created":"2024-08-09","cited_by_count":8,"area":null},{"id":"2408.13534","title":"Cultural Adaptation of Menus: A Fine-Grained Approach","created":"2024-08-24","cited_by_count":8,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2310.17353","title":"Cultural Adaptation of Recipes","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2312.01308","title":"Bridging Background Knowledge Gaps in Translation with Automatic Explicitation","created":"2023-12-03","cited_by_count":7,"area":null},{"id":"2406.13718","title":"Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2502.15972","title":"When Cultures Meet: Multicultural Text-to-Image Generation","created":"2025-02-21","cited_by_count":7,"area":null},{"id":"2302.10086","title":"A Two-Sided Discussion of Preregistration of NLP Research","created":"2023-02-20","cited_by_count":6,"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":"2311.15781","title":"Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2411.07417","title":"Untangling Hate Speech Definitions: A Semantic Componential Analysis Across Cultures and Domains","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2412.10281","title":"One world, one opinion? The superstar effect in LLM responses","created":"2024-12-13","cited_by_count":6,"area":null},{"id":"2304.12810","title":"Transcending the \"Male Code\": Implicit Masculine Biases in NLP Contexts","created":"2023-04-22","cited_by_count":5,"area":null},{"id":"2407.01091","title":"M2QA: Multi-domain Multilingual Question Answering","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2409.16646","title":"Cross-Lingual and Cross-Cultural Variation in Image Descriptions","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2501.13419","title":"A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2505.18322","title":"Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2506.01675","title":"Cross-Lingual Transfer of Cultural Knowledge: An Asymmetric Phenomenon","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2509.17399","title":"DIWALI: Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2510.11563","title":"Culturally-Aware Conversations: A Framework & Benchmark for LLMs","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2602.16201","title":"Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2311.08348","title":"MC$^2$: Towards Transparent and Culturally-Aware NLP for Minority Languages in China","created":"2023-11-14","cited_by_count":4,"area":null},{"id":"2408.06062","title":"On Tables with Numbers, with Numbers","created":"2024-08-12","cited_by_count":4,"area":null},{"id":"2410.12691","title":"Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2410.19419","title":"KAHANI: Culturally-Nuanced Visual Storytelling Tool for Non-Western Cultures","created":"2024-10-25","cited_by_count":4,"area":null},{"id":"2507.00216","title":"Towards Style Alignment in Cross-Cultural Translation","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2507.16442","title":"Dutch CrowS-Pairs: Adapting a Challenge Dataset for Measuring Social Biases in Language Models for Dutch","created":"2025-07-22","cited_by_count":4,"area":null},{"id":"2511.21695","title":"EvalCards: A Framework for Standardized Evaluation Reporting","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2310.14572","title":"Unveiling the Multi-Annotation Process: Examining the Influence of Annotation Quantity and Instance Difficulty on Model Performance","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2409.15380","title":"Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino","created":"2024-09-20","cited_by_count":3,"area":null}],"next_cursor":"100"}