[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-semantic-metrics":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"3ca23d77-e4c4-42c7-9cf4-c781700a4ef5","semantic metrics","semantic-metrics",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"32cc2350-8bcf-4970-9bcd-900a05441f2f","llms-for-asr-evaluation-beyond-wer-en","LLMs for ASR Evaluation: Beyond WER","This paper tests decoder-based LLMs as ASR evaluators and finds they beat WER on human agreement, with 92–94% on one task.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777010993439-cjdi.png","en","2026-04-24T06:09:38.008767+00:00"]