{"total":16,"rows":[{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35,"area":"alignment"},{"id":"2407.06443","title":"Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment","created":"2024-07-08","cited_by_count":25,"area":"alignment"},{"id":"2408.01420","title":"Mission Impossible: A Statistical Perspective on Jailbreaking LLMs","created":"2024-08-02","cited_by_count":24,"area":"alignment"},{"id":"2310.16960","title":"Privately Aligning Language Models with Reinforcement Learning","created":"2023-10-25","cited_by_count":17,"area":"alignment"},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2502.17515","title":"Towards User-level Private Reinforcement Learning with Human Feedback","created":"2025-02-22","cited_by_count":14,"area":"alignment"},{"id":"2504.16438","title":"POPri: Private Federated Learning using Preference-Optimized Synthetic Data","created":"2025-04-23","cited_by_count":14,"area":"alignment"},{"id":"2603.22563","title":"Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling","created":"2026-03-23","cited_by_count":3,"area":"alignment"},{"id":"2505.08849","title":"Improved Algorithms for Differentially Private Language Model Alignment","created":"2025-05-13","cited_by_count":2,"area":"alignment"},{"id":"2508.06783","title":"PROPS: Progressively Private Self-alignment of Large Language Models","created":"2025-08-09","cited_by_count":1,"area":"alignment"},{"id":"2605.30808","title":"Differentially Private Preference Data Synthesis for Large Language Model Alignment","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2606.10217","title":"Alignment Defends LLMs from Property Inference Attacks","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2603.03054","title":"PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"id":"2608.05040","title":"Private Direct Preference Optimization for LLM Alignment","created":"2026-08-05","cited_by_count":0,"area":"alignment"},{"id":"2610.16458","title":"Differential Privacy Protected Preference Alignment on Survey Derived Data","created":"2026-10-12","cited_by_count":0,"area":"alignment"}],"next_cursor":null}