身份与观点如何塑造大语言模型（LLM）中的政治奉承行为
How Identity and Opinion Shape Political Sycophancy in LLMs
浏览论文内容
中文总结 AI 辅助
该研究提出框架区分LLM政治奉承的观点与身份触发因素，经450个政治困境评估13个指令调优LLM，发现二者易感性解离、信号次可加，表明LLM政治立场具交互可引导脆弱性。
中文摘要 AI 辅助
随着大语言模型（LLM）越来越鼓励用户披露个人资料以提供定制化协助，衡量其政治对齐度变得愈发重要。然而，许多现有的评估政治行为的基准依赖封闭式问题，未能充分捕捉模型在交互过程中其立场如何适应用户提供的上下文。我们引入一个框架，将政治奉承的两个不同触发因素区分开来：观点（与明确叙述对齐）和身份（基于人口统计标签的刻板印象）。我们使用450个经人工核查的政治困境作为受控探针，评估了13个指令调优的LLM。我们发现了一种解离现象：模型对明确观点的易感性不一定能预测其对身份线索的易感性，反之亦然。当两种信号同时存在时，它们的影响通常是次可加的，而非简单相加。此外，系统层面的角色主要会改变模型的基线立场，而对由用户观点或身份导致的立场改变影响有限。最终，我们的结果表明，LLM的政治立场是可交互且可引导地脆弱，而非固定特征，凸显了个性化可能会放大模型行为中由身份或观点条件引发的转变。
英文摘要
As Large Language Models (LLMs) increasingly encourage users to disclose personal profiles for tailored assistance, measuring their political alignment becomes increasingly important. However, many existing benchmarks for assessing political behavior rely on closed-ended questions and do not fully capture how a model's stance may adapt to user-provided context during interaction. We introduce a framework that disentangles two distinct triggers of political sycophancy: opinion (aligning with explicit narratives) and identity (stereotyping based on demographic labels). Using 450 manually-checked political dilemmas as controlled probes, we evaluate 13 instruction-tuned LLMs. We uncover a dissociation: a model's susceptibility to explicit opinions does not necessarily predict its susceptibility to identity cues, and vice versa. When both signals are present, their effects are generally sub-additive rather than simply additive. Additionally, system-level personas primarily shift a model's baseline stance while having limited effect on the stance shift caused by user opinion or identity. Ultimately, our results suggest that LLM political stance is interactively and steerably vulnerable rather than being a fixed trait, highlighting how personalization may amplify identity- or opinion-conditioned shifts in the model's behaviors.
发表机构
- National Yang Ming Chiao Tung University（国立阳明交通大学）
- Academia Sinica（中央研究院）
- Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）
机构由 AI 辅助整理，请以论文原文为准。
