{"total":13,"rows":[{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2510.15859","title":"InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training","created":"2025-10-17","cited_by_count":12,"area":"alignment"},{"id":"2408.15625","title":"CBF-LLM: Safe Control for LLM Alignment","created":"2024-08-28","cited_by_count":9,"area":"alignment"},{"id":"2502.03095","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms","created":"2025-02-05","cited_by_count":8,"area":"alignment"},{"id":"2512.23457","title":"Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following","created":"2025-12-29","cited_by_count":8,"area":"alignment"},{"id":"2510.23751","title":"Debiasing Reward Models by Representation Learning with Guarantees","created":"2025-10-27","cited_by_count":6,"area":"alignment"},{"id":"2602.14777","title":"Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment","created":"2026-02-16","cited_by_count":6,"area":"alignment"},{"id":"2602.03160","title":"VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models","created":"2026-02-03","cited_by_count":3,"area":"alignment"},{"id":"2602.16835","title":"NeST: Neuron Selective Tuning for LLM Safety","created":"2026-02-18","cited_by_count":2,"area":"alignment"},{"id":"2506.00415","title":"Wide Reflective Equilibrium in LLM Alignment: Bridging Moral Epistemology and AI Safety","created":"2025-05-31","cited_by_count":0,"area":"alignment"},{"id":"2509.07642","title":"Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment","created":"2025-09-09","cited_by_count":0,"area":"alignment"},{"id":"2511.03121","title":"Control Barrier Function for Aligning Large Language Models","created":"2025-11-05","cited_by_count":0,"area":"alignment"},{"id":"2605.19665","title":"CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging","created":"2026-05-19","cited_by_count":0,"area":"alignment"}],"next_cursor":null}