arXiv cs.CL· Akram Elbouanani, Yousra Taleb, Gianluca Demartini, Adrian Popescu·· 11 小时前AI 评分48
用户属性与政治意识形态如何影响 LLM 在网络政治辩论中的接受度
User Attributes and Political Ideology Shape LLM Receptiveness in Online Political Debates
AI 导读
研究将 5,376 场网络辩论重构为 LLM 对话并运行近 150,000 次受控多轮对话，发现 LLM 对左倾用户的接受度系统性高于右倾用户。该不对称在双方辩护同一立场或对手同场出现时依然存在，说明不能完全由立场一致或对话者迎合解释；重复交互会提升接受度但不消除这一排序，专业水平也有影响，修辞差异较小。该模式出现在多个模型中，但可通过不同政治语料微调大幅消除或逆转。
正文 · 原文
Abstract:Online political discussions increasingly involve AI-mediated participation, as users invoke LLMs to assess contested claims, arbitrate disputes, and respond to opposing viewpoints. As these systems become participants in online exchanges, they may alter which speakers and argumentative strategies receive validation within the discussion.
We study this interactional dimension by reconstructing 5,376 this http URL debates as LLM conversations and running nearly 150,000 controlled multi-turn conversations that vary user political orientation, expertise, rhetorical strategy, and defended position, including conversations with competing users.
Across naturalistic and controlled debates, we find that LLMs are systematically more receptive to left-leaning than right-leaning users. The asymmetry persists when users with different political orientations defend the same position and when opposing users appear in the same conversation, indicating that it is not fully explained by stance agreement or simple accommodation to the current speaker. Repeated interaction increases receptiveness without eliminating this ordering; expertise also matters, while rhetorical differences are smaller. The pattern appears across multiple models, but is not fixed: fine-tuning on different political corpora can largely erase or reverse it. These results show that LLMs can respond systematically differently to participants in the same political debate, making such interactional asymmetries important for understanding their emerging role in online public discourse.
| Comments: | Preprint. Submitted for conference review |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.02908 [cs.AI] |
| (or arXiv:2611.02908v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.02908 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Akram Elbouanani [view email]
[v1]
Mon, 2 Nov 2026 10:40:22 UTC (1,329 KB)
来源：arXiv cs.CL · arxiv.org