{"total":14,"rows":[{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2412.12497","title":"NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning","created":"2024-12-17","cited_by_count":37,"area":"alignment"},{"id":"2405.17931","title":"Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment","created":"2024-05-28","cited_by_count":28,"area":"alignment"},{"id":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2412.01253","title":"Yi-Lightning Technical Report","created":"2024-12-02","cited_by_count":12,"area":"alignment"},{"id":"2410.06293","title":"Accelerated Preference Optimization for Large Language Model Alignment","created":"2024-10-08","cited_by_count":5,"area":"alignment"},{"id":"2410.08458","title":"Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both","created":"2024-10-11","cited_by_count":5,"area":"alignment"},{"id":"2608.11698","title":"REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation","created":"2026-08-12","cited_by_count":3,"area":"alignment"},{"id":"2405.18952","title":"Are You Sure? Rank Them Again: Repeated Ranking For Better Preference Datasets","created":"2024-05-29","cited_by_count":1,"area":"alignment"},{"id":"2503.01233","title":"PEO: Improving Bi-Factorial Preference Alignment with Post-Training Policy Extrapolation","created":"2025-03-03","cited_by_count":1,"area":"alignment"},{"id":"2503.03460","title":"Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models","created":"2025-03-05","cited_by_count":1,"area":"alignment"},{"id":"2503.04346","title":"Adding Alignment Control to Language Models","created":"2025-03-06","cited_by_count":0,"area":"alignment"}],"next_cursor":null}