---
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](https://lasrlabs.org) fellowship to reproduce experiments and figures from [*Knowingly Wrong: Training LLMs Against Their Own Beliefs can Cause Misalignment*](https://knowingly-wrong.github.io/).

## Structure

### wrongness/
### persona-vectors/
### realistic-scenarios/