Paper Detail
Xinnong Zhang, Wanting Shan, Hanjia Lyu, Zhongyu Wei, Jiebo Luo
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{zhang2026revising,
title = {Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions},
author = {Xinnong Zhang and Wanting Shan and Hanjia Lyu and Zhongyu Wei and Jiebo Luo},
year = {2026},
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 tar},
url = {https://arxiv.org/abs/2606.06443},
keywords = {cs.CL, cs.MM, cs.SI, large language models, stance simulation, counterfactual context revision, conversational context, multimodal approach, polarization-preference mechanisms, stance transition rate, huggingface daily},
eprint = {2606.06443},
archiveprefix = {arXiv},
}
{}