修订语境，转变模拟立场：审计基于LLM的在线讨论立场模拟

摘要

大型语言模型日益被用于模拟社交媒体用户，并推断个体可能如何回应在线讨论。然而，目前尚不清楚这些模拟是反映了精确的用户特定信念，还是对对话语境中语义无关的变化高度敏感。在本研究中，我们探讨了反事实语境修订作为一种审计基于大语言模型立场模拟的框架。给定一段原始在线对话，我们首先推断目标用户对特定话题的立场。然后，我们对对话语境应用受控的修订策略，并在修订后的语境下再次模拟用户的立场。我们比较了纯文本修订策略与融入模因语境的多模态策略，并评估了两个主要有效性指标，即平均方向性立场偏移和立场转变率。结果表明，在不同的极化偏好机制下，纯文本和多模态策略均能实现有效且稳健的立场转变。我们的研究贡献了一个评估框架，用于理解基于大语言模型的立场模拟对语境的敏感性。更广泛而言，它突显了使用大语言模型模拟在线舆论动态的前景与风险。

English

Large language models are increasingly used to simulate social media users and infer how individuals may respond to online discussions. However, it remains unclear whether these simulations reflect precise user-specific beliefs or whether they are highly sensitive to semantically independent changes in conversational contexts. In this work, we study counterfactual context revision as a framework for auditing LLM-based stance simulation. Given an original online conversation, we first infer a target user's stance toward a specific topic. We then apply controlled revision strategies to the conversational context and simulate the user's stance again under the revised context. We compare text-only revision strategies with a multimodal one that incorporates meme-based context and evaluate two main effectiveness metrics, i.e., average directional stance shift and stance transition rate. The results reveal effective and robust stance transitions in both text-only and multimodal strategies across different polarization-preference mechanisms. Our study contributes an evaluation framework for understanding the context sensitivity of LLM-based stance simulation. More broadly, it highlights both the promise and risk of using LLMs to simulate online opinion dynamics.