{"ID":3083568,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T05:32:54.120957816Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.06443","arxiv_id":"2606.06443","title":"Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions","abstract":"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.","short_abstract":"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 c...","url_abs":"https://arxiv.org/abs/2606.06443","url_pdf":"https://arxiv.org/pdf/2606.06443v1","authors":"[\"Xinnong Zhang\",\"Wanting Shan\",\"Hanjia Lyu\",\"Zhongyu Wei\",\"Jiebo Luo\"]","published":"2026-06-04T17:41:54Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.MM\",\"cs.SI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}