This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
ApartSprints
AI Testing
Accepted at the 
AI Testing
 research sprint on 
December 19, 2022

Discovering Latent Knowledge in Language Models Without Supervision - extensions and testing

Based on the paper "Discovering Latent Knowledge in Language Models without supervision" this project discusses how well the proposed method applies to the concept of ambiguity. To do that, we tested the Contrast Consistent Search method on data with clear cut (0 or 1) or ambiguous (0,5) examples.

By 
Agatha Duzan, Matthieu David, Jonathan Claybrough
🏆 
4th place
3rd place
2nd place
1st place
 by peer review