When Agents Persuade: Rhetoric Generation and Mitigation in LLMs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jose, Julia, Roongta, Ritik, Greenstadt, Rachel
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911559298580480
author Jose, Julia
Roongta, Ritik
Greenstadt, Rachel
author_facet Jose, Julia
Roongta, Ritik
Greenstadt, Rachel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_04636
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle When Agents Persuade: Rhetoric Generation and Mitigation in LLMs
Jose, Julia
Roongta, Ritik
Greenstadt, Rachel
Artificial Intelligence
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.
title When Agents Persuade: Rhetoric Generation and Mitigation in LLMs
topic Artificial Intelligence
url https://arxiv.org/abs/2603.04636