[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-reinforcement-fine-tuning":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"f0b38be2-6635-4c0e-95e3-b79ae36aba0e","reinforcement fine-tuning","reinforcement-fine-tuning",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"f659bb6c-0788-4653-a1b6-53f8798c8564","microsoft-goalcover-fine-tuning-gaps-zh","Microsoft GoalCover 找出微調缺口","Microsoft Research 的 GoalCover 會在微調前找出資料缺口，並在 Qwen-3-14B 的金融摘要任務上提升 reward 分數。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778462447499-4gq4.png","zh","2026-05-11T01:20:33.736263+00:00"]