This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
ApartSprints
Deception Detection Hackathon: Preventing AI deception
660d65646a619f5cf53b1f56
Deception Detection Hackathon: Preventing AI deception
July 1, 2024
Accepted at the 
660d65646a619f5cf53b1f56
 research sprint on 

Boosting Language Model Honesty with Truthful Suffixes

We investigate the construction of truthful suffixes, which cause models to provide more truthful responses to user queries. Prior research has focused on the use of adversarial suffixes for jailbreaking; we extend this to causing truthful behaviour.

By 
Smitty van Bodegom, Giles Edkins, Annie Szorkin
🏆 
4th place
3rd place
2nd place
1st place
 by peer review
Thank you! Your submission is under review.
Oops! Something went wrong while submitting the form.

This project is private