{"total":20,"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":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"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":"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":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"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":"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":"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":"2508.09016","title":"A Survey on Training-free Alignment of Large Language Models","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"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":"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":"2604.04261","title":"APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs","created":"2026-04-05","cited_by_count":1,"area":"alignment"},{"id":"2606.18606","title":"Steerable Cultural Preference Optimization of Reward Models","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2601.17096","title":"Beyond Instrumental and Substitutive Paradigms: Introducing Machine Culture as an Emergent Phenomenon in Large Language Models","created":"2026-01-23","cited_by_count":0,"area":"alignment"},{"id":"2603.06264","title":"Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2604.25654","title":"Progressing beyond Art Masterpieces or Touristic Clich\\'es: how to assess your LLMs for cultural alignment?","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2608.01458","title":"PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs","created":"2026-08-02","cited_by_count":0,"area":"alignment"},{"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":"2608.29492","title":"CoCoA: Context-Conditional Cultural Alignment for Large Language Models","created":"2026-08-30","cited_by_count":0,"area":"alignment"},{"id":"2609.38555","title":"Demographic Pluralism: Inference-Time Modeling of Pluralistic Human Preference Distributions","created":"2026-09-29","cited_by_count":0,"area":"alignment"}],"next_cursor":null}