arXiv Open Access 2026

When Agents Persuade: Rhetoric Generation and Mitigation in LLMs

Julia Jose Ritik Roongta Rachel Greenstadt
Lihat Sumber

Abstrak

Despite their wide-ranging benefits, LLM-based agents deployed in open environments can be exploited to produce manipulative material. In this study, we task LLMs with propaganda objectives and analyze their outputs using two domain-specific models: one that classifies text as propaganda or non-propaganda, and another that detects rhetorical techniques of propaganda (e.g., loaded language, appeals to fear, flag-waving, name-calling). Our findings show that, when prompted, LLMs exhibit propagandistic behaviors and use a variety of rhetorical techniques in doing so. We also explore mitigation via Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and ORPO (Odds Ratio Preference Optimization). We find that fine-tuning significantly reduces their tendency to generate such content, with ORPO proving most effective.

Topik & Kata Kunci

Penulis (3)

J

Julia Jose

R

Ritik Roongta

R

Rachel Greenstadt

Format Sitasi

Jose, J., Roongta, R., Greenstadt, R. (2026). When Agents Persuade: Rhetoric Generation and Mitigation in LLMs. https://arxiv.org/abs/2603.04636

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓