# When Large Language Models are More PersuasiveThan Incentivized Humans, and Why

arXiv: https://arxiv.org/abs/2505.09662 · HTML: https://mlsanity.com/paper/2505.09662/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 42 references that are in the map.
- First posted on arXiv 14 May 2025.

## Builds on (most cited first, 1 of 1)

- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)

## Built on by (most cited first, 13 of 13)

- [The Levers of Political Persuasion with Conversational AI](https://mlsanity.com/paper/2507.13919/) (2025)
- [Large Reasoning Models Are Autonomous Jailbreak Agents](https://mlsanity.com/paper/2508.04039/) (2025)
- [Harmful Traits of AI Companions](https://mlsanity.com/paper/2511.14972/) (2025)
- [Evaluating Language Models for Harmful Manipulation](https://mlsanity.com/paper/2603.25326/) (2026)
- [Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework](https://mlsanity.com/paper/2507.12872/) (2025)
- [AI systems out-persuade expert humans](https://mlsanity.com/paper/2606.16475/) (2026)
- [Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion](https://mlsanity.com/paper/2509.21054/) (2025)
- [AI advice suppresses people's willingness to say "I don't know", even when the advice is wrong and accuracy is incentivized](https://mlsanity.com/paper/2607.13562/) (2026)
- [What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates](https://mlsanity.com/paper/2607.02507/) (2026)
- [Polarization by Design: How Elites Could Shape Mass Preferences as AI Reduces Persuasion Costs](https://mlsanity.com/paper/2512.04047/) (2025)
- [Games That Teach, Chats That Convince: Comparing Interactive and Static Formats for Persuasive Learning](https://mlsanity.com/paper/2602.17905/) (2026)
- [The Hidden Costs of AI-Mediated Political Outreach: Persuasion and AI Penalties in the US and UK](https://mlsanity.com/paper/2603.27413/) (2026)
- [Toward Meaningful Transparency for AI Chatbots: Disclosing Persuasive Intent Reduces Persuasion](https://mlsanity.com/paper/2608.11794/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have been shown to be highly persuasive, but when and why they outperform humans is still an open question. We compare the persuasiveness of two LLMs (Claude 3.5 Sonnet and DeepSeek v3) against humans who had incentives to persuade, using an interactive, real-time conversational setting. We demonstrate that LLMs persuasive superiority is context-dependent: it depends on whether the persuasion attempt is truthful (towards the right answer) or deceptive (towards the wrong answer) and on the LLM model, and wanes over repeated interactions (unlike human persuasiveness). In our first large-scale experiment, humans vs LLMs (Claude 3.5 Sonnet) interacted with other humans who were completing an online quiz for a reward, attempting to persuade them toward a given (either correct or incorrect) answer. Claude was more persuasive than incentivized human persuaders both in truthful and deceptive contexts and it significantly increased accuracy if persuasion was truthful, but decreased it if persuasion was deceptive. In a follow-up experiment with Deepseek v3, we replicated the findings about accuracy but found greater LLM persuasiveness only if the persuasion was deceptive. Linguistic analyses of the persuaders texts suggest that these effects may be due to LLMs expressing higher conviction than humans.