2 papers
cs.LG2023
Comparing Optimization Targets for Contrast-Consistent Search
Hugo Fry, Seamus Fallows, Ian Fan +2
We investigate the optimization target of Contrast-Consistent Search (CCS), which aims to recover the internal representations of truth of a large language model. We present a new…
cs.LG2023
Low-Entropy Latent Variables Hurt Out-of-Distribution Performance
Nandi Schoots, Dylan Cope
We study the relationship between the entropy of intermediate representations and a model's robustness to distributional shift. We train models consisting of two feed-forward netwo…