1
Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users
鼠标和眼睛的微动作，竟能泄露你的偏好！这项研究用用户隐含反馈对齐大模型，摆脱对显式评价的依赖，开辟LLM训练新思路。
arXiv:2606.20482v1 Announce Type: cross Abstract: To align a Large Language Model (LLM), most existing methods collect explicit human feedback and tra…