arXiv cs.AI· Marco Tonin, Michele Tizzoni, Bruno Lepri, Luca Maria Aiello·· 12 小时前AI 评分31
用调查受访者报告的党派接触验证 LLM 生成的政治网络
Validating LLM-generated political networks with survey-reported partisan exposure
AI 导读
研究用 ANES 2020–2022 社交媒体调查中抽样的 persona 生成 LLM 政治网络，并以受访者自报的党派接触作为实证基准进行验证。部分模型生成的民主党与共和党 ego 之间隔离强于调查结果，同党接触更高、跨党接触更低，另一些模型则整体低估共和党接触。
正文 · 原文
Abstract:Large language models (LLMs) are increasingly used to simulate human behavior in social science research, including decisions, interactions, and social relationships. However, in network formation tasks, existing evaluations often focus on aggregate network properties, while networks with plausible structural properties may still fail to reproduce individuals' social and political environments. Here, we generate LLM-based political networks using personas sampled from the nationally representative ANES 2020--2022 Social Media Study and use respondents' survey-reported partisan exposure as an empirical benchmark for the political environments generated for the corresponding personas. We first characterize the structural properties and political assortativity of the generated networks, and then compare ego-level partisan exposure with the survey. We find that the structure and political assortativity of the generated networks vary across experimental configurations. More importantly, when comparing generated partisan exposure with the survey, some models generate stronger separation between Democratic and Republican egos than reported in the survey, with higher same-party and lower cross-party exposure, while others mainly underestimate Republican exposure across ego groups. Moreover, networks with similar political assortativity can still generate different partisan environments around the same personas, including among networks with plausible structural properties. Finally, generated networks show group-specific errors, under- or overestimating exposure to either Democrats or Republicans for specific social groups. These findings show that evaluating LLM-based social simulations only through aggregate outcomes can hide errors in the local environments through which those outcomes emerge, highlighting the importance of validation at both aggregate and individual levels.
| Subjects: | Social and Information Networks (cs.SI); Artificial Intelligence (cs.AI); Physics and Society (physics.soc-ph) |
| Cite as: | arXiv:2610.23199 [cs.SI] |
| (or arXiv:2610.23199v1 [cs.SI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23199 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Marco Tonin [view email]
[v1]
Fri, 16 Oct 2026 09:38:11 UTC (1,278 KB)
来源：arXiv cs.AI · arxiv.org