热点
"后训练对齐" 相关文章
Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization
cs.AI updates on arXiv.org 2025-07-11T04:04:14.000000Z
MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion
cs.AI updates on arXiv.org 2025-07-04T04:08:44.000000Z
最新「大模型简史」整理！从Transformer（2017）到DeepSeek-R1（2025）
智源社区 2025-03-02T15:37:13.000000Z