CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty

Summary

CATCH (Continuous Adversarial Training for Consistent Honesty) trains LLMs toward honest answers and away from dishonest ones while preserving capabilities, using only hundreds of targets built from self-reporting scenarios. The authors evaluate Llama-3.3-70B-Instruct and Qwen3-3.6-27B, reporting less dishonesty under pressure on MASK, more confessions in Among Us, and better discovery of hidden behaviours in AuditBench. CATCH matches state-of-the-art honesty activation steering and outperforms it on utility retention.