Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts. While prior work has documented conversational features correlated with sycophancy, we lack a systematic understanding of what provokes or prevents AI sycophancy. Here, we present a set of controlled experimental studies where we first isolate how input framing influences sycophancy, and second, leverage these findings to develop mitigation strategies. In a nested factorial design, we compare questions to various non-questions where we vary three orthogonal factors: epistemic certainty (statement, belief, conviction), perspective (I- vs user-perspective), and affirmation vs negation. We show that (1) sycophancy is substantially higher in response to non-questions compared to questions. Additionally, we find that (2) sycophancy increases monotonically with epistemic certainty conveyed by the user, and (3) is amplified by I-perspective framing. Building on this, we show that asking a model to convert non-questions into questions before answering significantly reduces sycophancy. Importantly, this effect is stronger than a simple baseline prompt asking models "not to be sycophantic". Our work offers a practical and effective input-level mitigation that both developers and users can easily adopt.

翻译：谄媚性，即大型语言模型倾向于提供迎合用户的回答而非批判性回应，已被视为一种对齐失败，在高风险咨询和社交情境中尤为突出。尽管先前研究记录了与谄媚性相关的对话特征，我们仍缺乏对引发或阻止AI谄媚性的系统性理解。本文提出一组受控实验研究：首先分离输入框架如何影响谄媚性，其次利用这些发现开发缓解策略。通过嵌套因子设计，我们比较了提问与各类非提问形式，并操控三个正交因素：认知确定性（陈述、信念、确信）、视角（第一人称vs用户视角）以及肯定vs否定。实验表明：(1) 相较于提问，模型对非提问的回应中谄媚性显著更高。此外发现(2) 谄媚性随用户传递的认知确定性程度单调递增，(3) 第一人称视角框架会放大谄媚效应。基于此，我们证明要求模型在回答前将非提问转化为提问能显著降低谄媚性。值得注意的是，该效果优于仅提示模型"不要谄媚"的简单基线方法。本研究提供了一种实用有效的输入级缓解策略，开发者和用户均可便捷采用。