The Rhetoric of Machine Learning

Robert C. Williamson

cs.LGApr 8, 2026

The Rhetoric of Machine Learning

Authors: Robert C. Williamson

Organizations: University of Tübingen & Tübingen AI Center

Abstract

I examine the technology of machine learning from the perspective of rhetoric, which is simply the art of persuasion. Rather than being a neutral and "objective" way to build "world models" from data, machine learning is (I argue) inherently rhetorical. I explore some of its rhetorical features, and examine one pervasive business model where machine learning is widely used, "manipulation as a service."

When Agents Persuade: Rhetoric Generation and Mitigation in LLMs
Mar 4, 2026Julia Jose, Ritik Roongta, Rachel GreenstadtPersuasion in Language Models LLM Agent Safety
Department of Computer Science and Engineering, New York University, New York, NY, USA
Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it
Jul 23, 2026Federico BoggiaLanguage Model Calibration
A Corpus of Persuasion Techniques in Slavic Languages
Jul 12, 2026Jakub Piskorski, Dimitar Iliyanov Dimitrov, Marina Ernst +4
Institute of Computer Science, Polish Academy of Science, Poland · Sofia University "St. Kliment Ohridski", Bulgaria · University of Koblenz, Germany +4

Mar 4, 2026J/K move · Enter open · S save

When Agents Persuade: Rhetoric Generation and Mitigation in LLMs

Julia Jose, Ritik Roongta, Rachel Greenstadt

Department of Computer Science and Engineering, New York University, New York, NY, USA

Persuasion in Language Models LLM Agent Safety Language Model Safety Evaluation

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

When Agents Persuade: Rhetoric Generation and Mitigation in LLMs

Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it

A Corpus of Persuasion Techniques in Slavic Languages