{"total":26,"rows":[{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2503.15484","title":"Value Profiles for Encoding Human Variation","created":"2025-03-19","cited_by_count":29,"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":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2502.01930","title":"Robust LLM Alignment via Distributionally Robust Direct Preference Optimization","created":"2025-02-04","cited_by_count":18,"area":"alignment"},{"id":"2412.03822","title":"Beyond the Binary: Capturing Diverse Preferences With Reward Regularization","created":"2024-12-05","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":"2503.01658","title":"CoPL: Collaborative Preference Learning for Personalizing LLMs","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2508.14460","title":"DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization","created":"2025-08-20","cited_by_count":7,"area":"alignment"},{"id":"2602.02033","title":"One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation","created":"2026-02-02","cited_by_count":5,"area":"alignment"},{"id":"2606.04284","title":"Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling","created":"2026-06-02","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":"2603.02225","title":"Scaling Reward Modeling without Human Supervision","created":"2026-02-11","cited_by_count":1,"area":"alignment"},{"id":"2604.03238","title":"RLHF May Not Reflect Genuine Preferences","created":"2026-01-31","cited_by_count":1,"area":"alignment"},{"id":"2502.18744","title":"ZEBRA: Leveraging Model-Behavioral Knowledge for Zero-Annotation Preference Dataset Construction","created":"2025-02-26","cited_by_count":0,"area":"alignment"},{"id":"2510.05465","title":"VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models","created":"2025-10-06","cited_by_count":0,"area":"alignment"},{"id":"2601.18751","title":"Trust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback","created":"2026-01-26","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":"2603.08412","title":"Aligning to Illusions: Choice Blindness in Human and AI Feedback","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2605.11865","title":"Variance-aware Reward Modeling with Anchor Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2606.03110","title":"Coherence Maximization Improves Pluralistic Alignment","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2608.06400","title":"Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Experts Reward Models via Contribution Contrast","created":"2026-07-31","cited_by_count":0,"area":"alignment"},{"id":"2608.30597","title":"PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.33803","title":"Diffusion Reward Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.34374","title":"ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.38647","title":"Uncertainty-Normalized Margins for Direct Preference Optimization","created":"2026-09-29","cited_by_count":0,"area":"alignment"}],"next_cursor":null}