Towards Robust Model Organisms for Eliciting Latent Knowledge

TL;DR: We argue that a useful model organism should satisfy three properties: selectivity, robustness, and retention. We build a model organism for finding security vulnerabilities in code which selectively withholds hard vulnerabilities, and is more resistant to standard elicitation methods like pirate training and weak-to-strong generalization than prior MOs.The desired sandbagging behavior on our code vulnerability scanning task involves selectively withholding hard-to-find vulnerabilities. A...