Skip to content

Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions

Jun 2026 · arXiv.org · Vol abs/2606.06443 · 0 citations · 36 references
Computer Science

TL;DR

This work studies counterfactual context revision as a framework for auditing LLM-based stance simulation and reveals effective and robust stance transitions in both text-only and multimodal strategies across different polarization-preference mechanisms.

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 (https://github.com/STARResearchLab/StanceShift). More broadly, it highlights both the promise and risk of using LLMs as proxies for social media users in social simulation.

View source

Similar papers

Book Open access Sep 2026

Who Changes Their Mind? Exploring Stance Shifts in LLM-Based Social Media Simulations

Understanding the dynamics of stance change on social media is crucial for addressing polarization and information integrity, yet observational studies face challenges including limited experimental control, restricted data access, and algorithmic confounds. We leverage Generative Agent-Based Modeling (GABM)—a novel si...

Valerio La Gatta, Gian Marco Orlando, Marco Perillo et al. · 1 citation
#natural language process... Preprint Sep 2026

DyMT-ESB: Dynamic Multi-Turn Evaluation of Social Bias in User-LLM Interactions

Experimental results show that LLMs exhibit social bias even in coherent, response-conditioned multi-turn interactions, revealing late-emerging bias, non-monotonic bias patterns, and bias re-emergence, which motivate evaluations that extend beyond fixed-turn, pre-scripted protocols.

Rem Hida, Masahiro Kaneko, Daisuke Oba et al. · 1 citation
#artificial intelligence Preprint Aug 2026

How Identity and Opinion Shape Political Sycophancy in LLMs

A framework that disentangles two distinct triggers of political sycophancy: opinion (aligning with explicit narratives) and identity (stereotyping based on demographic labels) is introduced, highlighting how personalization may amplify identity- or opinion-conditioned shifts in the model's behaviors.

Li-Ni Fu, Chang-Chih Meng, Chien-Hua Chen et al. · 0 citations

Framing the Narrative: Ideological Mimicry in Large Language Models

Large language models (LLMs) are increasingly used to answer questions about politically contentious issues, yet evaluations typically treat a model's stance as a relatively stable property. Real users, however, communicate political signals through their terminology, assumptions, and personal context. We investigate w...

Olivia Macmillan-Scott, Michael B. Jacobs, Nils W. Metternich et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.