{"total":32,"rows":[{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"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":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124,"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":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2405.01525","title":"FLAME: Factuality-Aware Alignment for Large Language Models","created":"2024-05-02","cited_by_count":47,"area":"alignment"},{"id":"2405.20850","title":"Improving Reward Models with Synthetic Critiques","created":"2024-05-31","cited_by_count":44,"area":"alignment"},{"id":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41,"area":"alignment"},{"id":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2402.11253","title":"Aligning Large Language Models by On-Policy Self-Judgment","created":"2024-02-17","cited_by_count":20,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2402.11296","title":"Dissecting Human and LLM Preferences","created":"2024-02-17","cited_by_count":17,"area":"alignment"},{"id":"2606.04923","title":"Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning","created":"2026-06-03","cited_by_count":16,"area":"alignment"},{"id":"2506.07326","title":"Reward Model Interpretability via Optimal and Pessimal Tokens","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2503.01894","title":"LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2409.18618","title":"Model-based Preference Optimization in Abstractive Summarization without Human Feedback","created":"2024-09-27","cited_by_count":7,"area":"alignment"},{"id":"2410.11677","title":"Understanding Likelihood Over-optimisation in Direct Alignment Algorithms","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2509.18632","title":"A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users","created":"2025-09-23","cited_by_count":6,"area":"alignment"},{"id":"2408.10270","title":"SEAL: Systematic Error Analysis for Value ALignment","created":"2024-08-16","cited_by_count":4,"area":"alignment"},{"id":"2412.20834","title":"Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment","created":"2024-12-30","cited_by_count":4,"area":"alignment"},{"id":"2405.13541","title":"Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts","created":"2024-05-22","cited_by_count":3,"area":"alignment"},{"id":"2406.12416","title":"Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models","created":"2024-06-18","cited_by_count":2,"area":"alignment"},{"id":"2505.20088","title":"Multi-Domain Explainability of Preferences","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2601.18061","title":"Expert Evaluation and the Limits of Human Feedback in Mental Health AI Safety Testing","created":"2026-01-26","cited_by_count":2,"area":"alignment"},{"id":"2411.01245","title":"PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment","created":"2024-11-02","cited_by_count":1,"area":"alignment"},{"id":"2602.15338","title":"Discovering Implicit Large Language Model Alignment Objectives","created":"2026-02-17","cited_by_count":0,"area":"alignment"},{"id":"2605.00155","title":"Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2605.26840","title":"Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2607.22305","title":"A Roadmap to Impactful Pluralistic Alignment Research","created":"2026-07-24","cited_by_count":0,"area":"alignment"}],"next_cursor":null}