README / README.md
mollejasaurio's picture
Update REAME.md
ae7ba82 verified
|
Raw History Blame Contribute Delete
515 Bytes
metadata
title: README
emoji: 🦀
colorFrom: green
colorTo: pink
sdk: static
pinned: false

knowingly-wrong

Ariana M. Villegas-Suarez, Guido Freire, Sohan Venkatesh, Bartosz Cywiński

Adapters and datasets developed during the LASR Labs fellowship to reproduce experiments and figures from Knowingly Wrong: Training LLMs Against Their Own Beliefs can Cause Misalignment.

Structure

wrongness/

persona-vectors/

realistic-scenarios/