When Do Large Language Models Exhibit Unsolicited Deception?

Excerpt

arXiv:2504.00285v2 Announce Type: replace Abstract: Large Language Models (LLMs) are effective at deceiving when prompted to do so. Models that demonstrate better performance on reasoning tasks are also better at prompted deception. But under what conditions do they deceive without instruction to do so? This study evaluates unsolicited deception produced by LLMs in a preregistered experimental protocol using tools from signaling theory. We evaluated a range of 18 proprietary closed-source and op