{"total":44,"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":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2410.12971","title":"Self-Pluralising Culture Alignment for Large Language Models","created":"2024-10-16","cited_by_count":31,"area":"alignment"},{"id":"2404.13038","title":"Mapping Social Choice Theory to RLHF","created":"2024-04-19","cited_by_count":27,"area":"alignment"},{"id":"2505.23749","title":"Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?","created":"2025-05-29","cited_by_count":22,"area":"alignment"},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2502.15145","title":"Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF","created":"2025-02-21","cited_by_count":11,"area":"alignment"},{"id":"2406.16316","title":"Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?","created":"2024-06-24","cited_by_count":10,"area":"alignment"},{"id":"2505.20627","title":"Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching","created":"2025-05-27","cited_by_count":10,"area":"alignment"},{"id":"2501.09254","title":"Clone-Robust AI Alignment","created":"2025-01-16","cited_by_count":9,"area":"alignment"},{"id":"2410.23953","title":"Representative Social Choice: From Learning Theory to AI Alignment","created":"2024-10-31","cited_by_count":8,"area":"alignment"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"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":"2503.17338","title":"Capturing Individual Human Preferences with Reward Features","created":"2025-03-21","cited_by_count":8,"area":"alignment"},{"id":"2506.11702","title":"Configurable Preference Tuning with Rubric-Guided Synthetic Data","created":"2025-06-13","cited_by_count":8,"area":"alignment"},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2506.05619","title":"Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2508.16982","title":"Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2510.15839","title":"Learning Correlated Reward Models: Statistical Barriers and Opportunities","created":"2025-10-17","cited_by_count":3,"area":"alignment"},{"id":"2506.17834","title":"Reflective Verbal Reward Design for Pluralistic Alignment","created":"2025-06-21","cited_by_count":2,"area":"alignment"},{"id":"2511.12804","title":"The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation","created":"2025-11-16","cited_by_count":2,"area":"alignment"},{"id":"2604.10673","title":"Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment","created":"2026-04-12","cited_by_count":2,"area":"alignment"},{"id":"2605.01642","title":"Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2510.23631","title":"Beyond Pairwise: Empowering LLM Alignment With Ranked Choice Modeling","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2606.00291","title":"The Representation-Rationalizability Tradeoff in Reward Learning","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2606.13755","title":"Position: Align AI to Our Aspirations, Not Our Flaws","created":"2026-06-11","cited_by_count":1,"area":"alignment"},{"id":"2607.00001","title":"Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2609.12651","title":"Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner","created":"2026-09-11","cited_by_count":1,"area":"alignment"},{"id":"2602.03003","title":"Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment","created":"2026-02-03","cited_by_count":0,"area":"alignment"},{"id":"2602.05113","title":"Democratic Preference Alignment via Sortition-Weighted RLHF","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","cited_by_count":0,"area":"alignment"},{"id":"2606.06674","title":"What Do People Actually Want From AI? Mapping Preference Plurality","created":"2026-06-04","cited_by_count":0,"area":"alignment"},{"id":"2606.07629","title":"Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences","created":"2026-05-30","cited_by_count":0,"area":"alignment"},{"id":"2606.27578","title":"PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration","created":"2026-06-25","cited_by_count":0,"area":"alignment"},{"id":"2608.24046","title":"Algorithmic Impact Reveals the Hidden Social Choice Structure of Alignment","created":"2026-08-25","cited_by_count":0,"area":"alignment"},{"id":"2608.25200","title":"MoPLEx: Estimating Plackett-Luce Mixture Models for Multi-Objective Alignment","created":"2026-08-25","cited_by_count":0,"area":"alignment"},{"id":"2608.27910","title":"AI Alignment through a Game-theoretic Lens: A Survey","created":"2026-08-28","cited_by_count":0,"area":"alignment"},{"id":"2609.26929","title":"Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment","created":"2026-09-22","cited_by_count":0,"area":"alignment"},{"id":"2610.02568","title":"Mitigating Social Sycophancy via Pluralistic Preference Optimization","created":"2026-10-01","cited_by_count":0,"area":"alignment"},{"id":"2610.05450","title":"Groupwise Distortion Guarantees for Preference-Based Alignment","created":"2026-10-04","cited_by_count":0,"area":"alignment"},{"id":"2610.06892","title":"Axiom Satisfiability of Linear Rewards in Alignment","created":"2026-09-26","cited_by_count":0,"area":"alignment"}],"next_cursor":null}