{"total":34,"rows":[{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129,"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":"2502.19190","title":"Provocations from the Humanities for Generative AI Research","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2505.23785","title":"Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale","created":"2025-05-23","cited_by_count":10,"area":null},{"id":"2511.21322","title":"TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories","created":"2025-11-26","cited_by_count":10,"area":null},{"id":"2604.16403","title":"Computational Hermeneutics: Evaluating generative AI as a cultural technology","created":"2026-03-31","cited_by_count":8,"area":null},{"id":"2512.07075","title":"Do Large Language Models Truly Understand Cross-cultural Differences?","created":"2025-12-08","cited_by_count":6,"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":"2511.18852","title":"FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models","created":"2025-11-24","cited_by_count":5,"area":null},{"id":"2506.00784","title":"Research Borderlands: Analysing Writing Across Research Cultures","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2508.00673","title":"MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2505.18562","title":"From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2510.03541","title":"What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2510.27672","title":"Culture Cartography: Mapping the Landscape of Cultural Knowledge","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2602.00065","title":"Responsible Evaluation of AI for Mental Health","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2503.19642","title":"Exploring Cultural Nuances in Emotion Perception Across 15 African Languages","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2602.03709","title":"No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.15949","title":"BanglaSocialBench: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of LLMs in Bangladeshi Social Interaction","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2605.15990","title":"Defining Cultural Capabilities for AI Evaluation: A Taxonomy Grounded in Intercultural Communication Theory","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2608.12894","title":"BavGround: A Benchmark for Regional Cultural Grounding and Dialect Competence in Bavarian","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2506.22968","title":"Against 'softmaxing' culture","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2509.21946","title":"Debiasing Large Language Models in Thai Political Stance Detection via Counterfactual Calibration","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2601.02858","title":"To Generate or Discriminate? Methodological Considerations for Measuring Cultural Alignment in LLMs","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2603.26013","title":"Toward Culturally Grounded Natural Language Processing","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.09945","title":"Cross-Cultural Value Attribution in Large Vision-Language Models","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.02601","title":"SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.26955","title":"JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.00333","title":"Which Institutional Frameworks Do Chatbots Assume? Auditing Jurisdictional Defaults in Multilingual LLMs","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.02459","title":"Language Models as Measurement Apparatus for Culture","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.05405","title":"CCBENCH: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queries","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.21445","title":"When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.15191","title":"What Limits Us? Analyzing Self-Reported Limitations in NLP Research","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.32281","title":"Supporting and Performing Culture from the Inside","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}