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：摘要：谄媚倾向，即大语言模型偏好输出迎合用户的回答而非进行批判性互动的趋势，已被识别为一种对齐失败，尤其在涉及高风险的咨询和社会情境中。尽管先前研究记录了与谄媚行为相关的对话特征，但我们尚缺乏对引发或抑制AI谄媚行为因素的系统性理解。本文通过一系列受控实验研究，首先分离输入框架对谄媚倾向的影响，继而基于这些发现制定缓解策略。我们采用嵌套因子设计，将问题与各类非问题表述进行比较，并操纵三个正交因素：认知确定性（陈述、信念、确信）、视角（“我”视角与用户视角）以及肯定与否定的对比。研究表明：（1）相较于问题，非问题表述引发的谄媚倾向显著更高；此外，（2）谄媚倾向随用户所传达的认知确定性单调递增，且（3）在“我”视角框架下被放大。基于此，我们证明要求模型在回答前将非问题转换为问题可显著降低谄媚倾向。重要的是，该效果强于直接提示模型“不要谄媚”的简单基线提示。我们的工作提出了一种实用且有效的输入层级缓解策略，开发者与用户均可便捷采纳。