Large language models generate political networks with realist exposure errors
Validating LLM-generated political networks with survey-reported partisan exposure
Social and Information NetworksArtificial Intelligence
Summary
This study looks at how well large language models (LLMs) can create fake social networks that reflect real political views and connections. The authors compare these model-generated networks to actual survey data about people’s political exposures. They find that while the overall network structures can look plausible, the fake networks often get individual political environments wrong, sometimes exaggerating how separate political groups are or misrepresenting exposure for certain social groups. This means it’s important to check these models not just for big-picture features but also for how they represent individual experiences.
What this means in practice
- •For political data analysts: Improve evaluation methods for political network simulations by validating individual partisan exposures against survey data.
- •For social media platform engineers: Refine algorithms that model user interaction networks to better reflect actual partisan mixing and exposure in online communities.
Authors
Marco Tonin, Michele Tizzoni, Bruno Lepri, Luca Maria Aiello
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.