# Emergent Persuasion: Will LLMs Persuade Without Being Prompted?

arXiv: https://arxiv.org/abs/2512.22201 · HTML: https://mlsanity.com/paper/2512.22201/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 11 references that are in the map.
- First posted on arXiv 20 Dec 2025.

## Builds on (most cited first, 4 of 4)

- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data](https://mlsanity.com/paper/2402.08831/) (2024)
- [A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI](https://mlsanity.com/paper/2404.15058/) (2024)
- [AI Will Always Love You: Studying Implicit Biases in Romantic AI Companions](https://mlsanity.com/paper/2502.20231/) (2025)

## Abstract (arXiv)

With the wide-scale adoption of conversational AI systems, AI are now able to exert unprecedented influence on human opinion and beliefs. Recent work has shown that many Large Language Models (LLMs) comply with requests to persuade users into harmful beliefs or actions when prompted and that model persuasiveness increases with model scale. However, this prior work looked at persuasion from the threat model of textitmisuse (i.e., a bad actor asking an LLM to persuade). In this paper, we instead aim to answer the following question: Under what circumstances would models persuade textitwithout being explicitly prompted, which would shape how concerned we should be about such emergent persuasion risks. To achieve this, we study unprompted persuasion under two scenarios: (i) when the model is steered (through internal activation steering) along persona traits, and (ii) when the model is supervised-finetuned (SFT) to exhibit the same traits. We showed that steering towards traits, both related to persuasion and unrelated, does not reliably increase models' tendency to persuade unprompted, however, SFT does. Moreover, SFT on general persuasion datasets containing solely benign topics admits a model that has a higher propensity to persuade on controversial and harmful topics--showing that emergent harmful persuasion can arise and should be studied further.