[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-distillation":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":9},"a6bb7f9c-bf74-4e21-920b-019ddd1e2da3","distillation",3,"蒸餾是把大型模型的推理能力、排序偏好或生成行為，轉移到較小模型的訓練方法。它常用於降低推論成本、縮短延遲，並讓 SLM 在重排、生成與跨架構對齊上更實用。","Distillation transfers a larger model’s behavior—ranking preferences, generation patterns, or reasoning signals—into a smaller student model. It matters because teams use it to cut inference cost and latency while keeping SLMs useful for reranking, generation, and cross-architecture alignment.",[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"678dca5c-61e1-411d-8e03-22f74e7fb823","select-to-think-slms-local-sufficiency-zh","讓小模型自己重排候選詞","S2T 讓小型語言模型先產生候選詞，再學會自己重排，不必每次都呼叫大型模型。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777530651973-to5d.png","zh","2026-04-30T06:30:34.439906+00:00"]