{"total":36,"rows":[{"id":"2402.09063","title":"Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space","created":"2024-02-14","cited_by_count":91,"area":"alignment"},{"id":"2402.09267","title":"Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation","created":"2024-02-14","cited_by_count":80,"area":"alignment"},{"id":"2404.16369","title":"Don't Say No: Jailbreaking LLM by Suppressing Refusal","created":"2024-04-25","cited_by_count":56,"area":"alignment"},{"id":"2405.10301","title":"Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees","created":"2024-05-16","cited_by_count":54,"area":"alignment"},{"id":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2311.14743","title":"A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shift","created":"2023-11-21","cited_by_count":18,"area":"alignment"},{"id":"2403.00199","title":"Improving Socratic Question Generation using Data Augmentation and Preference Optimization","created":"2024-03-01","cited_by_count":16,"area":"alignment"},{"id":"2403.19279","title":"Fine-Tuning Language Models with Reward Learning on Policy","created":"2024-03-28","cited_by_count":15,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2309.10202","title":"Stabilizing RLHF through Advantage Model and Selective Rehearsal","created":"2023-09-18","cited_by_count":14,"area":"alignment"},{"id":"2502.07340","title":"Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering","created":"2025-02-11","cited_by_count":12,"area":"alignment"},{"id":"2403.03419","title":"Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization","created":"2024-03-06","cited_by_count":11,"area":"alignment"},{"id":"2411.16502","title":"Interpreting Language Reward Models via Contrastive Explanations","created":"2024-11-25","cited_by_count":9,"area":"alignment"},{"id":"2310.00898","title":"Enabling Language Models to Implicitly Learn Self-Improvement","created":"2023-10-02","cited_by_count":7,"area":"alignment"},{"id":"2507.15507","title":"Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback","created":"2025-07-21","cited_by_count":6,"area":"alignment"},{"id":"2508.02618","title":"Alleviating Attention Hacking in Discriminative Reward Modeling through Interaction Distillation","created":"2025-08-04","cited_by_count":5,"area":"alignment"},{"id":"2510.17833","title":"Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage","created":"2025-10-03","cited_by_count":5,"area":"alignment"},{"id":"2310.00819","title":"Parameter-Efficient Tuning Helps Language Model Alignment","created":"2023-10-01","cited_by_count":4,"area":"alignment"},{"id":"2504.09895","title":"Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data","created":"2025-04-14","cited_by_count":4,"area":"alignment"},{"id":"2604.05279","title":"Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition","created":"2026-04-07","cited_by_count":4,"area":"alignment"},{"id":"2511.21050","title":"Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs","created":"2025-11-26","cited_by_count":3,"area":"alignment"},{"id":"2503.23362","title":"Mixture of Routers","created":"2025-03-30","cited_by_count":2,"area":"alignment"},{"id":"2507.21406","title":"Shapley Uncertainty in Natural Language Generation","created":"2025-07-29","cited_by_count":2,"area":"alignment"},{"id":"2501.15219","title":"Faster Machine Translation Ensembling with Reinforcement Learning and Competitive Correction","created":"2025-01-25","cited_by_count":1,"area":"alignment"},{"id":"2510.23334","title":"Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models","created":"2025-10-27","cited_by_count":1,"area":"alignment"},{"id":"2511.03731","title":"MimiTalk: Revolutionizing Qualitative Research with Dual-Agent AI","created":"2025-09-27","cited_by_count":1,"area":"alignment"},{"id":"2601.12758","title":"VISPA: Pluralistic Alignment via Automatic Value Selection and Activation","created":"2026-01-19","cited_by_count":1,"area":"alignment"},{"id":"2606.18606","title":"Steerable Cultural Preference Optimization of Reward Models","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2404.06390","title":"Latent Distance Guided Alignment Training for Large Language Models","created":"2024-04-09","cited_by_count":0,"area":"alignment"},{"id":"2405.15230","title":"$i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization","created":"2024-05-24","cited_by_count":0,"area":"alignment"},{"id":"2504.04657","title":"ACE-RLHF: Automated Code Evaluation and Socratic Feedback Generation Tool using Large Language Models and Reinforcement Learning with Human Feedback","created":"2025-04-07","cited_by_count":0,"area":"alignment"},{"id":"2506.02018","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","created":"2025-05-28","cited_by_count":0,"area":"alignment"},{"id":"2604.02766","title":"Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs","created":"2026-04-03","cited_by_count":0,"area":"alignment"},{"id":"2604.14895","title":"Beyond Importance Sampling: Rejection-Gated Policy Optimization","created":"2026-04-16","cited_by_count":0,"area":"alignment"},{"id":"2604.24429","title":"A Multi-Dimensional Audit of Politically Aligned Large Language Models","created":"2026-04-27","cited_by_count":0,"area":"alignment"},{"id":"2609.07808","title":"You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs","created":"2026-09-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}