{"total":54,"rows":[{"id":"2502.16761","title":"Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions","created":"2025-02-24","cited_by_count":66,"area":null},{"id":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61,"area":"alignment"},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2504.14439","title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling","created":"2025-04-20","cited_by_count":38,"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":"2410.03868","title":"Can Language Models Reason about Individualistic Human Values and Preferences?","created":"2024-10-04","cited_by_count":34,"area":"lr"},{"id":"2408.15549","title":"WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback","created":"2024-08-28","cited_by_count":31,"area":"alignment"},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2503.15463","title":"From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment","created":"2025-03-19","cited_by_count":30,"area":"alignment"},{"id":"2506.05598","title":"SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs","created":"2025-06-05","cited_by_count":29,"area":"alignment"},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","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":"2412.20299","title":"No Preference Left Behind: Group Distributional Preference Optimization","created":"2024-12-28","cited_by_count":21,"area":"alignment"},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2412.11167","title":"Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette","created":"2024-12-15","cited_by_count":16,"area":"agents"},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"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":"2505.24846","title":"MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning","created":"2025-05-30","cited_by_count":11,"area":"alignment"},{"id":"2509.19333","title":"Pluralistic Off-policy Evaluation and Alignment","created":"2025-09-15","cited_by_count":11,"area":"alignment"},{"id":"2410.16665","title":"SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior","created":"2024-10-22","cited_by_count":10,"area":null},{"id":"2503.01658","title":"CoPL: Collaborative Preference Learning for Personalizing LLMs","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2510.00177","title":"PrefDisco: Benchmarking Proactive Personalized Reasoning","created":"2025-09-30","cited_by_count":7,"area":"lr"},{"id":"2604.07343","title":"Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization","created":"2026-04-08","cited_by_count":7,"area":"alignment"},{"id":"2510.17881","title":"POPI: Personalizing LLMs via Optimized Natural Language Preference Inference","created":"2025-10-17","cited_by_count":6,"area":null},{"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":"2511.19458","title":"Personalized Reward Modeling for Text-to-Image Generation","created":"2025-11-21","cited_by_count":4,"area":"alignment"},{"id":"2602.12116","title":"P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling","created":"2026-02-12","cited_by_count":4,"area":"alignment"},{"id":"2604.12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2510.12817","title":"From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2509.03672","title":"SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences","created":"2025-09-03","cited_by_count":2,"area":"alignment"},{"id":"2502.01127","title":"The Battling Influencers Game: Nash Equilibria Structure of a Potential Game and Implications to Value Alignment","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2602.20759","title":"Overton Pluralistic Reinforcement Learning for Large Language Models","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2604.03238","title":"RLHF May Not Reflect Genuine Preferences","created":"2026-01-31","cited_by_count":1,"area":"alignment"},{"id":"2607.24900","title":"Inverse RL Helps Align AI by Imitating Humans","created":"2026-07-27","cited_by_count":1,"area":"alignment"},{"id":"2508.04476","title":"Metric Learning in an RKHS","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2511.05018","title":"Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies","created":"2025-11-07","cited_by_count":0,"area":null},{"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":"2603.08145","title":"DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2605.07162","title":"CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.09119","title":"Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.11240","title":"When to Ask a Question: Understanding Communication Strategies in Generative AI Tools","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.11865","title":"Variance-aware Reward Modeling with Anchor Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2606.10569","title":"Hidden Consensus:Preference-Validity Compression in Human Feedback","created":"2026-06-09","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"},{"id":"2609.22170","title":"Multiple latent orderings better predict language model preferences","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2609.32382","title":"PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35695","title":"Rethinking Personalized Generation: Test-Time Alignment via Factorized Ranking Models","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.05898","title":"Collaborative Personalized Preference Alignment for LLMs under Data Deficiency","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.12379","title":"Marformer: A Transformer for Predicting Missing Data Distributions","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}