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

Paper recorded by Signals 4 on 2026-10-15 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-15 on arXiv · recorded by Signals 4 on 2026-10-16

Category: cs.LG · 机器学习 · first seen 2026-10-16

Abstract

Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still exhibit dishonest behaviour, such as outputting claims that contradict some knowledge or are not supported by what is accessible in context. We introduce Continuous Adversarial Training for Consistent Honesty (CATCH), inspired by a method originally de

Read on arXiv →