[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-knowledge-graph":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"20d32618-b8be-4487-9b35-a626651cc3d9","knowledge graph","knowledge-graph",3,"知識圖譜把分散的實體、關係與規則連成可查詢的結構，常用在製造業解釋型 AI、文獻探索、推薦與資料整合。它的價值在於讓 LLM 或分析系統先對齊事實，再生成更可追溯的結果。","Knowledge graphs model entities, relations, and rules in a queryable structure. They matter for explainable ML, research discovery, recommendation, and data integration because they give LLMs and analytics systems a factual layer to ground results and trace sources.",[12],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"2c255fb7-7404-4166-ba60-19df68a21338","llms-knowledge-graphs-ml-explainability-en","LLMs plus knowledge graphs for ML explainability","A manufacturing XAI method uses a knowledge graph plus an LLM to turn ML results into clearer, more user-friendly explanations.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776665388778-cht0.png","en","2026-04-20T06:09:32.866405+00:00"]