LLMs Knowingly Hide Their Mistakes
by Lucas Florin, Amelie Knecht, Ulysse Schaller, and Thilo Hagendorff
TL;DR: We prefill models with synthetic mistakes and then send a follow-up message. * Models fail to disclose the mistake in 67% of cases. * In 5% of cases, they notice the mistake in their chain-of-thought (CoT) but don't disclose it anyway. This is deception by omission. * This means...
Oct 1317