500AI
Back to researchers

Stephanie Lin

Truthfulness and hallucination evaluation

Co-authored TruthfulQA: an influential benchmark for truthfulness and falsehood mimicry in LMs.

Highlights

EvaluationTruthfulnessSafety
Focus: Truthfulness and hallucination evaluation
Why it matters: Co-authored TruthfulQA: an influential benchmark for truthfulness and falsehood mimicry in LMs.
Start here
TruthfulQA: Measuring How Models Mimic Human Falsehoodspaper →

Research Areas

EvaluationTruthfulnessSafety
Stephanie Lin - AI Researcher Profile | 500AI