Back to researchers

Drew A. Hudson

Holistic evaluation of language models (HELM)

Co-authored HELM: a framework for evaluating language models across many axes beyond raw accuracy.

Highlights

EvaluationBenchmarksResponsible AI
Focus: Holistic evaluation of language models (HELM)
Why it matters: Co-authored HELM: a framework for evaluating language models across many axes beyond raw accuracy.

Research Areas

EvaluationBenchmarksResponsible AI
Drew A. Hudson - AI Researcher Profile | 500AI