paper-with-me

홈 › Papers

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

2026-06-04 · Xinnong Zhang, Wanting Shan, Hanjia Lyu, Zhongyu Wei, Jiebo Luo arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.06443

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Auditing Chinese Web-scale Corpora via Sampled BPE Token Statistics

2026-08-11 · Qingjie Zhang, Ziqi Tang, Jie Zhang, Gelei Deng 외 arxiv

Chinese web pollution has surfaced in LLMs, motivating audits of upstream Chinese corpora. However, auditing such corpora faces three challenges: (1) their web-scale size makes full scan costly; (2) prior analyses are of…

DECOR: Auditing LLM Deception via Information Manipulation Theory

2026-05-19 · Linyue Cai, Samuel Yeh, Jwala Dhamala, Rahul Gupta 외 arxiv

Large language models can deceive by subtly manipulating truthful information -- omitting key facts, shifting focus, or obscuring meaning -- making such behavior difficult to detect. Existing black-box methods rely on co…

Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions

2024-10-10 · Inderjeet Nair, Jiaye Tan, Xiaotian Su, Anne Gere 외

Providing feedback is widely recognized as crucial for refining students' writing skills. Recent advances in language models (LMs) have made it possible to automatically generate feedback that is actionable and well-alig…

Language ModelingLanguage Modelling

A Generative Approach for Semantic Auditing of Electronic Health Records

2025-07-03 · Irena Girshovitz, Atai Ambus, Moni Shahar, Ran Gilad-Bachrach arxiv

The reliability of clinical artificial intelligence (AI) depends on high-quality data, yet Electronic Health Records are often inconsistent with existing scientific knowledge. Current quality assessments are limited: the…

Gram: Assessing sabotage propensities via automated alignment auditing

2026-05-28 · David Lindner, Victoria Krakovna, Sebastian Farquhar arxiv

We introduce Gram, an automated alignment auditing framework to assess the propensity of AI agents to engage in sabotage. We evaluate Gemini models across 17 simulated agentic deployment scenarios that incentivize sabota…