{"total":15,"rows":[{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193,"area":"lr"},{"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":"2501.04167","title":"Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation","created":"2025-01-07","cited_by_count":27,"area":"lr"},{"id":"2502.14860","title":"ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning","created":"2025-02-20","cited_by_count":25,"area":"lr"},{"id":"2502.13131","title":"Rethinking Diverse Human Preference Learning through Principal Component Analysis","created":"2025-02-18","cited_by_count":10,"area":"lr"},{"id":"2402.03469","title":"Rethinking the Role of Proxy Rewards in Language Model Alignment","created":"2024-02-02","cited_by_count":7,"area":"lr"},{"id":"2505.18071","title":"Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2510.18526","title":"Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2509.23140","title":"Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement Learning","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2510.11194","title":"Aligning Deep Implicit Preferences by Learning to Reason Defensively","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2602.20528","title":"Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning","created":"2026-02-24","cited_by_count":2,"area":"lr"},{"id":"2603.10009","title":"Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2604.24996","title":"Sparse Personalized Text Generation with Multi-Trajectory Reasoning","created":"2026-04-27","cited_by_count":0,"area":"lr"},{"id":"2605.26969","title":"Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling","created":"2026-05-26","cited_by_count":0,"area":"lr"}],"next_cursor":null}