{"total":14,"rows":[{"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":"2406.05882","title":"Distributional Preference Alignment of LLMs via Optimal Transport","created":"2024-06-09","cited_by_count":26,"area":"alignment"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2502.10563","title":"Accelerating Unbiased LLM Evaluation via Synthetic Feedback","created":"2025-02-14","cited_by_count":7,"area":"alignment"},{"id":"2412.07192","title":"PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips","created":"2024-12-10","cited_by_count":5,"area":"alignment"},{"id":"2602.09411","title":"K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge","created":"2026-02-10","cited_by_count":4,"area":"alignment"},{"id":"2509.23982","title":"Toward Preference-aligned Large Language Models via Residual-based Model Steering","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2507.02850","title":"LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users","created":"2025-07-03","cited_by_count":2,"area":"alignment"},{"id":"2508.17018","title":"Limitations of refinement methods for weak to strong generalization","created":"2025-08-23","cited_by_count":1,"area":"alignment"},{"id":"2607.07918","title":"Efficient Safety Alignment of Language Models via Latent Personality Traits","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2607.08034","title":"PLURAL: A Global Dataset for Value Alignment","created":"2026-07-09","cited_by_count":1,"area":"alignment"},{"id":"2602.02898","title":"Aligning Language Model Benchmarks with Pairwise Preferences","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2605.00022","title":"Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment","created":"2026-04-20","cited_by_count":0,"area":"alignment"}],"next_cursor":null}