{"total":20,"rows":[{"id":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2405.19544","title":"One-Shot Safety Alignment for Large Language Models via Optimal Dualization","created":"2024-05-29","cited_by_count":24,"area":"alignment"},{"id":"2503.18991","title":"Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment","created":"2025-03-23","cited_by_count":20,"area":"alignment"},{"id":"2505.19387","title":"Alignment of large language models with constrained learning","created":"2025-05-26","cited_by_count":8,"area":"alignment"},{"id":"2410.19933","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","created":"2024-10-25","cited_by_count":5,"area":"alignment"},{"id":"2506.08266","title":"Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints","created":"2025-06-09","cited_by_count":4,"area":"alignment"},{"id":"2502.02153","title":"Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing","created":"2025-02-04","cited_by_count":3,"area":"alignment"},{"id":"2505.20359","title":"Risk-aware Direct Preference Optimization under Nested Risk Measure","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2604.00979","title":"Dual Optimal: Make Your LLM Peer-like with Dignity","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2604.17299","title":"Cat-DPO: Category-Adaptive Safety Alignment","created":"2026-04-19","cited_by_count":1,"area":"alignment"},{"id":"2510.05703","title":"Provably Convergent Primal-Dual DPO for Constrained LLM Alignment","created":"2025-10-07","cited_by_count":0,"area":"alignment"},{"id":"2510.26301","title":"Offline Clustering of Preference Learning with Active-data Augmentation","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2512.24263","title":"Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment","created":"2025-12-30","cited_by_count":0,"area":"alignment"},{"id":"2602.22146","title":"Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual","created":"2026-02-25","cited_by_count":0,"area":"alignment"},{"id":"2607.18258","title":"S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF","created":"2026-05-15","cited_by_count":0,"area":"alignment"},{"id":"2608.21278","title":"CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment","created":"2026-08-21","cited_by_count":0,"area":"alignment"},{"id":"2609.08634","title":"Suan: Rectifying Direct Preference Safety Alignment in Large Language Models","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2609.19325","title":"AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment","created":"2026-09-16","cited_by_count":0,"area":"alignment"}],"next_cursor":null}