Zhiyuan Zeng (@zhiyuanzeng_) 's Twitter Profile
Zhiyuan Zeng

@zhiyuanzeng_

PhD-ing @uwnlp @uwcse | Prev. @Tsinghua_Uni @TsinghuaNLP @princeton_nlp

ID: 1650962310880714753

linkhttp://zhiyuan-zeng.github.io calendar_today25-04-2023 20:37:54

174 Tweet

417 Takipçi

216 Takip Edilen

Zhiyuan Zeng (@zhiyuanzeng_) 's Twitter Profile Photo

Is a single accuracy number all we can get from model evals?🤔 🚨Does NOT tell where the model fails 🚨Does NOT tell how to improve it Introducing EvalTree🌳 🔍identifying LM weaknesses in natural language 🚀weaknesses serve as actionable guidance (paper&demo 🔗in🧵) [1/n]