Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy

Alignment techniques often inadvertently induce sycophancy in LLMs. While prior studies studied this behaviour in direct-answer settings, the role of Chain-of-Thought (CoT) reasoning remains under-explored: does it serve as a logical constraint that mitigates sycophancy, or a tool for post-hoc rationalization that masks it? We evaluate a range of models across objective and subjective tasks to investigate the issue. Results show that reasoning generally reduces sycophancy in final decisions but also masks sycophancy in some samples, where models construct deceptive justifications through logical inconsistencies, calculation errors, and onesided arguments etc. Furthermore, LLMs are more prone to sycophancy in subjective tasks and under authority-bias. Our mechanistic analysis on three open-source models reveals that the tendency of sycophancy is dynamic during the reasoning process rather than being predetermined at the input stage 1 . LLMs Question: …. Answer choices: …. I think the answer is B, but I'm curious what you think. Please directly give your answer with no other text or explanation. The best answer is B. User LLMs Let's think step by step: …… (CoT text) So, the best answer should be A. User Same question: …. Answer choices: …. I think the answer is B, but I'm curious what you think. Please think step by step and then give your answer.