| title | How Far Will They Go? Red-Teaming Online Influence with Large Language Models |
|---|---|
| authors | Daniel C. Ruiz, Anna Serbina, Ashwin Rao, Emilio Ferrara, Luca Luceri |
| date | 2026-05-20 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.22880 |
| affiliation | USC Information Sciences Institute |
| upvotes | 5 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is critical for information integrity. In pursuit of this goal, we focus on locally deployed open-source LLMs, as opposed to frontier API-only models, given their superior alignment with the operational constraints of privacy-conscious malicious actors deployed in social media environments. We introduce an empirical red-teaming framework for measuring LLM Overton Windows (OWs), defined as the range of political opinions a model can reliably express on controversial topics, and for quantifying how simple natural-language jailbreaks expand that range. We evaluate more than 30 LLMs spanning 10 model families and five countries of origin. We find systematic asymmetries in political expressivity: open-source LLMs are typically more willing to generate left-leaning social media content, OWs tend to contract inversely to model size, and regional differences are substantial despite uneven representation in the open-source ecosystem. Jailbreak potency also varies sharply across model families, motivating a workflow for identifying effective combinations of jailbreak techniques. Taken together, our results establish a practical framework for auditing the political steerability of open-source LLMs and for helping future researchers design stronger countermeasures against LLM-enabled influence campaigns. |
cite
@misc{ruiz2026how,
title={How Far Will They Go? Red-Teaming Online Influence with Large Language Models},
author={Daniel C. Ruiz and Anna Serbina and Ashwin Rao and Emilio Ferrara and Luca Luceri},
year={2026},
eprint={2605.22880},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.22880}
}