[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-llm-judges":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"a06663b2-7b41-4d4d-b4d1-893e47c35d7f","LLM judges","llm-judges",1,null,[11,20],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"50662a29-bae9-4d88-b8d8-3d6a83680646","judge-reliability-harness-stress-tests-llm-judges-en","Judge Reliability Harness Stress-Tests LLM Judges","A harness probes how LLM judges change under formatting, paraphrasing, verbosity, and flipped labels.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778740862456-3f4y.png","en","2026-05-14T06:40:33.380748+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"3a330546-beae-4173-9b71-9d0d446ff432","llm-judge-reliability-conformal-transitivity-en","How to Trust LLM Judges, Per Input","A diagnostic toolkit shows LLM judges can look stable on average while still being unreliable on individual inputs.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776406194842-ml7e.png","2026-04-17T06:09:33.415041+00:00"]