[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-preference-modeling":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"2f52e568-f1d5-4dd7-963c-5b75b13c81e0","preference modeling","preference-modeling",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"492aa1ec-02ce-491e-ad03-ae804f261f87","weak-rewards-persistent-llm-user-models-zh","弱回饋讓 LLM 記住偏好","這篇論文主張，可從檢索增強互動中抽出弱回饋，來建立可持續的使用者偏好模型。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779084838002-5od2.png","zh","2026-05-18T06:13:32.906335+00:00"]