# When Agents Persuade: Rhetoric Generation and Mitigation in LLMs

arXiv: https://arxiv.org/abs/2603.04636 · HTML: https://mlsanity.com/paper/2603.04636/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)
- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 23 of 23)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [A Categorical Archive of ChatGPT Failures](https://mlsanity.com/paper/2302.03494/) (2023)
- [Fine-Grained Analysis of Propaganda in News Articles](https://mlsanity.com/paper/1910.02517/) (2019)
- [On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial](https://mlsanity.com/paper/2403.14380/) (2024)
- [SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles](https://mlsanity.com/paper/2009.02696/) (2020)
- [A Survey on Computational Propaganda Detection](https://mlsanity.com/paper/2007.08024/) (2020)
- [SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images](https://mlsanity.com/paper/2105.09284/) (2021)
- [The Persuasive Power of Large Language Models](https://mlsanity.com/paper/2312.15523/) (2023)
- [A Pathway Towards Responsible AI Generated Content](https://mlsanity.com/paper/2303.01325/) (2023)
- [Overwriting Pretrained Bias with Finetuning Data](https://mlsanity.com/paper/2303.06167/) (2023)
- [Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language](https://mlsanity.com/paper/2406.17753/) (2024)
- [Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments](https://mlsanity.com/paper/2404.09329/) (2024)
- [Can GPT-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles](https://mlsanity.com/paper/2402.17478/) (2024)
- [ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them](https://mlsanity.com/paper/2005.07934/) (2020)
- [Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF](https://mlsanity.com/paper/2403.02513/) (2024)
- [Adapting Fake News Detection to the Era of Large Language Models](https://mlsanity.com/paper/2311.04917/) (2023)
- [It Takes Two to Negotiate: Modeling Social Exchange in Online Multiplayer Games](https://mlsanity.com/paper/2311.08666/) (2023)
- [Cross-Domain Learning for Classifying Propaganda in Online Contents](https://mlsanity.com/paper/2011.06844/) (2020)
- [Are Large Language Models Good at Detecting Propaganda?](https://mlsanity.com/paper/2505.13706/) (2025)

## Built on by (most cited first, 1 of 1)

- [Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs](https://mlsanity.com/paper/2608.11624/) (2026)

## Abstract (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.