{"total":103,"rows":[{"id":"2601.17087","title":"Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations","created":"2026-01-23","cited_by_count":40,"area":"agents"},{"id":"2501.08579","title":"LLM-based Human Simulations Have Not Yet Been Reliable","created":"2025-01-15","cited_by_count":30,"area":null},{"id":"2502.09083","title":"Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking","created":"2025-02-13","cited_by_count":29,"area":null},{"id":"2502.11995","title":"Presumed Cultural Identity: How Names Shape LLM Responses","created":"2025-02-17","cited_by_count":21,"area":null},{"id":"2509.02550","title":"PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture","created":"2025-09-02","cited_by_count":21,"area":null},{"id":"2503.19075","title":"The Case for \"Thick Evaluations\" of Cultural Representation in AI","created":"2025-03-24","cited_by_count":17,"area":null},{"id":"2504.05154","title":"CARE: Multilingual Human Preference Learning for Cultural Awareness","created":"2025-04-07","cited_by_count":15,"area":"alignment"},{"id":"2505.19484","title":"CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis","created":"2025-05-26","cited_by_count":15,"area":"synth"},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"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":"2505.21693","title":"MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs","created":"2025-05-27","cited_by_count":13,"area":null},{"id":"2509.19274","title":"DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture","created":"2025-09-23","cited_by_count":13,"area":null},{"id":"2508.21476","title":"Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards","created":"2025-08-29","cited_by_count":11,"area":"agents"},{"id":"2502.19190","title":"Provocations from the Humanities for Generative AI Research","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2509.01301","title":"Culture is Everywhere: A Call for Intentionally Cultural Evaluation","created":"2025-09-01","cited_by_count":10,"area":"alignment"},{"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":"2502.15972","title":"When Cultures Meet: Multicultural Text-to-Image Generation","created":"2025-02-21","cited_by_count":7,"area":null},{"id":"2509.24216","title":"MoVa: Towards Generalizable Classification of Human Morals and Values","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2505.21979","title":"Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset","created":"2025-05-28","cited_by_count":6,"area":"mllm"},{"id":"2509.10886","title":"CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis","created":"2025-09-13","cited_by_count":6,"area":"rag"},{"id":"2502.13497","title":"Towards Geo-Culturally Grounded LLM Generations","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2503.07237","title":"LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2503.16094","title":"Cultural Alignment in Large Language Models Using Soft Prompt Tuning","created":"2025-03-20","cited_by_count":5,"area":"alignment"},{"id":"2506.01565","title":"Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation","created":"2025-06-02","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":"2510.11563","title":"Culturally-Aware Conversations: A Framework & Benchmark for LLMs","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2511.14662","title":"Bias in, Bias out: Annotation Bias in Multilingual Large Language Models","created":"2025-11-18","cited_by_count":5,"area":null},{"id":"2412.17729","title":"Chumor 2.0: Towards Benchmarking Chinese Humor Understanding","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2505.10309","title":"A large-scale evaluation of commonsense knowledge in humans and large language models","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2505.13498","title":"IRLBench: A Multi-modal, Culturally Grounded, Parallel Irish-English Benchmark for Open-Ended LLM Reasoning Evaluation","created":"2025-05-16","cited_by_count":4,"area":"lr"},{"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":"2603.18300","title":"Auditing Preferences for Brands and Cultures in LLMs","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2506.00482","title":"Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2506.00784","title":"Research Borderlands: Analysing Writing Across Research Cultures","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2507.09701","title":"MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs","created":"2025-07-13","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":"2510.11178","title":"BLEnD-Vis: Benchmarking Multimodal Cultural Understanding in Vision Language Models","created":"2025-10-13","cited_by_count":3,"area":"mllm"},{"id":"2510.24328","title":"Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2510.24942","title":"Finding Culture-Sensitive Neurons in Vision-Language Models","created":"2025-10-28","cited_by_count":3,"area":"mllm"},{"id":"2511.22787","title":"World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models","created":"2025-11-27","cited_by_count":3,"area":"mllm"},{"id":"2602.06423","title":"On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2602.22475","title":"Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2603.21165","title":"Many Dialects, Many Languages, One Cultural Lens: Evaluating Multilingual VLMs for Bengali Culture Understanding Across Historically Linked Languages and Regional Dialects","created":"2026-03-22","cited_by_count":3,"area":null},{"id":"2504.02793","title":"A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2506.00312","title":"An evaluation of LLMs for generating movie reviews: GPT-4o, Gemini-2.0 and DeepSeek-V3","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2506.04975","title":"Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards","created":"2025-06-05","cited_by_count":2,"area":"safety"},{"id":"2508.17324","title":"CultranAI at PalmX 2025: Data Augmentation for Cultural Knowledge Representation","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2510.05291","title":"Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2601.03483","title":"CALM: Culturally Self-Aware Language Models","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2603.02370","title":"Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples","created":"2026-03-02","cited_by_count":2,"area":"mllm"},{"id":"2603.05723","title":"Cultural Perspectives and Expectations for Generative AI: A Global Survey Approach","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2605.05662","title":"XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity","created":"2026-05-07","cited_by_count":2,"area":"safety"},{"id":"2606.13808","title":"The Culture Funnel: You Can't Align What isn't in the Data","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2503.01947","title":"Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2503.21011","title":"Can Large Language Models Predict Associations Among Human Attitudes?","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2505.21937","title":"Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.01719","title":"Towards culturally-appropriate conversational AI for health in the majority world: An exploratory study with citizens and professionals in Latin America","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2508.18709","title":"Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2509.04432","title":"Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki","created":"2025-09-04","cited_by_count":1,"area":"lr"},{"id":"2511.03180","title":"BengaliMoralBench: A Benchmark for Auditing Moral Reasoning in Large Language Models within Bengali Language and Culture","created":"2025-11-05","cited_by_count":1,"area":"lr"},{"id":"2512.17394","title":"Are Vision Language Models Cross-Cultural Theory of Mind Reasoners?","created":"2025-12-19","cited_by_count":1,"area":"lr"},{"id":"2601.12091","title":"Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debate","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"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":"2603.16827","title":"Prompt Programming for Cultural Bias and Alignment of Large Language Models","created":"2026-03-17","cited_by_count":1,"area":"alignment"},{"id":"2604.06210","title":"Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2604.21751","title":"Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.12515","title":"Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation","created":"2026-04-02","cited_by_count":1,"area":"alignment"},{"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":"2605.23069","title":"DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge","created":"2026-05-21","cited_by_count":1,"area":"mechinterp"},{"id":"2608.14079","title":"The conditional superiority of fast silicon sampling","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2504.05009","title":"Deconstructing Jazz Piano Style Using Machine Learning","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2504.05995","title":"NativQA Framework: Enabling LLMs and VLMs with Native, Local, and Everyday Knowledge","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2504.06313","title":"Text-to-Image Models and Their Representation of People from Different Nationalities Engaging in Activities","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2508.05502","title":"MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs","created":"2025-08-07","cited_by_count":0,"area":"mllm"},{"id":"2509.12961","title":"Do LLMs Understand Wine Descriptors Across Cultures? A Benchmark for Cultural Adaptations of Wine Reviews","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2601.12921","title":"Injecting Knowledge from Social Science Journals to Improve Indonesian Cultural Understanding by LLMs","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.01161","title":"The Role of Dataset Linguistic Structure in the Cultural Awareness of Large Language Models","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.10964","title":"Can LLMs Cook Jamaican Couscous? A Study of Cultural Novelty in Recipe Generation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.17283","title":"Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.08275","title":"AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models","created":"2026-03-09","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":"2604.02557","title":"Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.22002","title":"When Cow Urine Cures Constipation on YouTube: Limits of LLMs in Detecting Culture-specific Health Misinformation","created":"2026-04-23","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":"2605.27296","title":"Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.29897","title":"ExCAM: Explainable Cultural Awareness Metrics","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30481","title":"When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models","created":"2026-05-28","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":"2606.02493","title":"Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maxims","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.07877","title":"Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.12443","title":"Occupational Prompting Reveals Cultural Bias in Large Language Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.20258","title":"Editorial Alignment: A Participatory Approach to Engaging Editorial Expertise in LLM-mediated Knowledge Dissemination","created":"2026-06-18","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":"2608.09937","title":"Carefully Considering Culture: Analyzing LLM Alignment in Single- and Multi-Cultural Settings using Cultural Consensus Theory","created":"2026-05-29","cited_by_count":0,"area":"alignment"},{"id":"2608.21853","title":"PUMA: A Polish Benchmark for Culturally Grounded Multimodal Understanding","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.30107","title":"AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00491","title":"MemeBridge: A Dataset for Benchmarking and Mitigating the Bidirectional Cultural Gap in Meme Interpretation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.11772","title":"Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understanding","created":"2026-09-10","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}],"next_cursor":"100"}