{"total":13,"rows":[{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240,"area":"alignment"},{"id":"2412.06000","title":"Does RLHF Scale? Exploring the Impacts From Data, Model, and Method","created":"2024-12-08","cited_by_count":23,"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":"2412.01253","title":"Yi-Lightning Technical Report","created":"2024-12-02","cited_by_count":12,"area":"alignment"},{"id":"2503.04222","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","created":"2025-03-06","cited_by_count":6,"area":"alignment"},{"id":"2510.14616","title":"Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures","created":"2025-10-16","cited_by_count":6,"area":"alignment"},{"id":"2404.00604","title":"Extensive Self-Contrast Enables Feedback-Free Language Model Alignment","created":"2024-03-31","cited_by_count":4,"area":"alignment"},{"id":"2506.01495","title":"C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2503.22115","title":"Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories","created":"2025-03-28","cited_by_count":2,"area":"alignment"},{"id":"2508.14947","title":"Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization","created":"2025-08-20","cited_by_count":1,"area":"alignment"},{"id":"2409.02118","title":"TSO: Self-Training with Scaled Preference Optimization","created":"2024-08-31","cited_by_count":0,"area":"alignment"},{"id":"2504.05535","title":"COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values","created":"2025-04-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}