[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-judge-reliability":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"fd362d3d-ea54-48b9-af59-6ed53d862b11","judge reliability","judge-reliability",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"94547a94-aa6b-4c4f-9d64-31eb0b906947","policy-invariance-llm-safety-judge-test-en","Policy Invariance as a Better LLM Judge Test","This paper argues that accuracy alone is not enough to trust LLM safety judges, and proposes policy invariance as a reliability test.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778568046410-5agq.png","en","2026-05-12T06:40:28.372648+00:00"]