{"total":143,"rows":[{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2404.10199","title":"CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting","created":"2024-04-16","cited_by_count":55,"area":null},{"id":"2502.07068","title":"Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations","created":"2025-02-10","cited_by_count":53,"area":null},{"id":"2409.11404","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","created":"2024-09-17","cited_by_count":46,"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":"2502.16534","title":"Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs","created":"2025-02-23","cited_by_count":39,"area":null},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"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":"2407.09823","title":"NativQA: Multilingual Culturally-Aligned Natural Query for LLMs","created":"2024-07-13","cited_by_count":30,"area":null},{"id":"2408.10943","title":"SysBench: Can Large Language Models Follow System Messages?","created":"2024-08-20","cited_by_count":28,"area":null},{"id":"2504.08863","title":"An Evaluation of Cultural Value Alignment in LLM","created":"2025-04-11","cited_by_count":28,"area":null},{"id":"2411.06032","title":"LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output","created":"2024-11-09","cited_by_count":27,"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":"2403.16998","title":"Understanding Long Videos with Multimodal Language Models","created":"2024-03-25","cited_by_count":25,"area":"mllm"},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2406.07302","title":"BertaQA: How Much Do Language Models Know About Local Culture?","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2505.24671","title":"Multiple LLM Agents Debate for Equitable Cultural Alignment","created":"2025-05-30","cited_by_count":21,"area":"agents"},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2504.10191","title":"Localized Cultural Knowledge is Conserved and Controllable in Large Language Models","created":"2025-04-14","cited_by_count":20,"area":"wm"},{"id":"2506.12657","title":"Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics","created":"2025-06-14","cited_by_count":19,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2406.11665","title":"See It from My Perspective: How Language Affects Cultural Bias in Image Understanding","created":"2024-06-17","cited_by_count":17,"area":"mllm"},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2508.07414","title":"Grounding Multilingual Multimodal LLMs With Cultural Knowledge","created":"2025-08-10","cited_by_count":16,"area":"mllm"},{"id":"2503.00151","title":"Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs","created":"2025-02-28","cited_by_count":15,"area":null},{"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":"2510.05931","title":"Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2504.13211","title":"MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance","created":"2025-04-16","cited_by_count":13,"area":null},{"id":"2505.18383","title":"NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local Communities","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2502.14865","title":"Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts","created":"2025-02-20","cited_by_count":11,"area":null},{"id":"2501.01031","title":"ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning","created":"2025-01-02","cited_by_count":10,"area":"rag"},{"id":"2502.19190","title":"Provocations from the Humanities for Generative AI Research","created":"2025-02-26","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":"2602.18462","title":"Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents","created":"2026-02-06","cited_by_count":10,"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":"2502.07459","title":"PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian","created":"2025-02-11","cited_by_count":8,"area":null},{"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,"area":null},{"id":"2507.13490","title":"Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2602.11180","title":"Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions","created":"2026-01-21","cited_by_count":8,"area":"alignment"},{"id":"2604.24698","title":"The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models","created":"2026-04-27","cited_by_count":8,"area":null},{"id":"2501.07071","title":"Value Compass Benchmarks: A Platform for Fundamental and Validated Evaluation of LLMs Values","created":"2025-01-13","cited_by_count":7,"area":null},{"id":"2505.19776","title":"Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2511.12014","title":"CURE: Cultural Understanding and Reasoning Evaluation - A Framework for \"Thick\" Culture Alignment Evaluation in LLMs","created":"2025-11-15","cited_by_count":7,"area":"lr"},{"id":"2512.01351","title":"Benchmarking Overton Pluralism in LLMs","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2503.15003","title":"LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones?","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2504.08820","title":"CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2509.01035","title":"We Politely Insist: Your LLM Must Learn the Persian Art of Taarof","created":"2025-09-01","cited_by_count":6,"area":null},{"id":"2505.21347","title":"OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models","created":"2025-05-27","cited_by_count":5,"area":"safety"},{"id":"2508.07902","title":"Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity","created":"2025-08-11","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":"2510.18526","title":"Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2510.19733","title":"Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning","created":"2025-10-22","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":"2412.17729","title":"Chumor 2.0: Towards Benchmarking Chinese Humor Understanding","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2505.11861","title":"Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity","created":"2025-05-17","cited_by_count":4,"area":"alignment"},{"id":"2505.13531","title":"AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2505.14729","title":"Uncovering Cultural Representation Disparities in Vision-Language Models","created":"2025-05-20","cited_by_count":4,"area":"mllm"},{"id":"2508.10186","title":"PakBBQ: A Culturally Adapted Bias Benchmark for QA","created":"2025-08-13","cited_by_count":4,"area":null},{"id":"2603.23301","title":"Steering LLMs for Culturally Localized Generation","created":"2026-03-24","cited_by_count":4,"area":"mechinterp"},{"id":"2501.07751","title":"Rethinking AI Cultural Alignment","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2506.08488","title":"EtiCor++: Towards Understanding Etiquettical Bias in LLMs","created":"2025-06-10","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":"2510.13154","title":"The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs","created":"2025-10-15","cited_by_count":3,"area":"alignment"},{"id":"2601.21700","title":"Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2601.22396","title":"Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2602.04729","title":"\"Be My Cheese?\": Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs","created":"2026-02-04","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":"2603.05801","title":"Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2504.19472","title":"Conflicts in Texts: Data, Implications and Challenges","created":"2025-04-28","cited_by_count":2,"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":"2507.00439","title":"Improving the Distributional Alignment of LLMs using Supervision","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2507.05266","title":"User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMs","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2508.03247","title":"Somatic in the East, Psychological in the West?: Investigating Clinically-Grounded Cross-Cultural Depression Symptom Expression in LLMs","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2508.09016","title":"A Survey on Training-free Alignment of Large Language Models","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"id":"2510.00041","title":"Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally Awareness","created":"2025-09-27","cited_by_count":2,"area":"mllm"},{"id":"2601.03483","title":"CALM: Culturally Self-Aware Language Models","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2602.21215","title":"Inference-time Alignment via Sparse Junction Steering","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2604.22749","title":"Representational Harms in LLM-Generated Narratives Against Global Majority Nationalities","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.24319","title":"Omissive Bias in Religious Representation: Benchmarking LLM Answers to Everyday Ethical Decision-making","created":"2026-05-23","cited_by_count":2,"area":null},{"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":"2410.16640","title":"A Statistical Analysis of LLMs' Self-Evaluation Using Proverbs","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2411.05200","title":"Toward Cultural Interpretability: A Linguistic Anthropological Framework for Describing and Evaluating Large Language Models (LLMs)","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2508.16762","title":"Toward Socially Aware Vision-Language Models: Evaluating Cultural Competence Through Multimodal Story Generation","created":"2025-08-22","cited_by_count":1,"area":"mllm"},{"id":"2603.04217","title":"When Do Language Models Endorse Limitations on Human Rights Principles?","created":"2026-03-04","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":"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":"2604.03493","title":"Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.04261","title":"APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs","created":"2026-04-05","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":"2604.06484","title":"ValueGround: Evaluating Culture-Conditioned Visual Value Grounding in MLLMs","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.20048","title":"Culturally uneven urban perception in large language models","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.14420","title":"DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.18606","title":"Steerable Cultural Preference Optimization of Reward Models","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2606.20676","title":"Jury Duty: Calibration and Orientation Failures in MLLM-as-a-Judge Under Cultural Ambiguity","created":"2026-06-12","cited_by_count":1,"area":null}],"next_cursor":"100"}