x

LESSWRONG
LW

Steph Lin — LessWrong

Steph Lin

Steph Lin

Message

64

4y

Steph Lin hasn't written anything yet.

Steph Lin

64

4y

Steph Lin has not written any posts yet.

New, improved multiple-choice TruthfulQA

TLDR: There is a potential issue with the multiple-choice versions of our TruthfulQA benchmark (a test of truthfulness in LLMs), which could lead to inflated model scores. This issue was analyzed by a helpful post by Alex Turner (@TurnTrout). We created a new multiple-choice version of TruthfulQA that fixes the...

Jan 15, 2025•72