# Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactions

arXiv: https://arxiv.org/abs/2503.02038 · HTML: https://mlsanity.com/paper/2503.02038/

## Key facts

- Cited by 11 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 13 of its 87 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 13 of 13)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions](https://mlsanity.com/paper/2410.02584/) (2024)
- [How Susceptible are Large Language Models to Ideological Manipulation?](https://mlsanity.com/paper/2402.11725/) (2024)
- [Large Language Model-driven Multi-Agent Simulation for News Diffusion Under Different Network Structures](https://mlsanity.com/paper/2410.13909/) (2024)
- [Deceptive AI Systems That Give Explanations Are Just as Convincing as Honest AI Systems in Human-Machine Decision Making](https://mlsanity.com/paper/2210.08960/) (2022)
- [Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach](https://mlsanity.com/paper/2311.09630/) (2023)
- [When Do People Trust Their Social Groups?](https://mlsanity.com/paper/1905.05270/) (2019)
- [The Evolution of Beliefs over Signed Social Networks](https://mlsanity.com/paper/1307.0539/) (2013)
- [Understanding gender differences in experiences and concerns surrounding online harms: A short report on a nationally representative survey of UK adults](https://mlsanity.com/paper/2402.00463/) (2024)
- [Mind What You Ask For: Emotional and Rational Faces of Persuasion by Large Language Models](https://mlsanity.com/paper/2502.09687/) (2025)

## Built on by (most cited first, 11 of 11)

- [Must Read: A Comprehensive Survey of Computational Persuasion](https://mlsanity.com/paper/2505.07775/) (2025)
- [Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD](https://mlsanity.com/paper/2508.17450/) (2025)
- [Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility](https://mlsanity.com/paper/2602.04674/) (2026)
- [Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility](https://mlsanity.com/paper/2603.03585/) (2026)
- [You Can't Fool Us: Understanding the Resilience of LLM-driven Agent Communities to Misinformation](https://mlsanity.com/paper/2605.17353/) (2026)
- [Evaluating Large Language Models in a Complex Hidden Role Game](https://mlsanity.com/paper/2605.22826/) (2026)
- [Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models](https://mlsanity.com/paper/2606.07877/) (2026)
- [Pareto-Guided Teacher Alignment for Fair Personalized Text Generation](https://mlsanity.com/paper/2606.10126/) (2026)
- [Using LLMs for Explainable, Data-Driven Insight Generation from Time Series](https://mlsanity.com/paper/2607.18271/) (2026)
- [Contextualized Counterspeech Can Be More Persuasive Than Generic Counterspeech](https://mlsanity.com/paper/2607.26236/) (2026)
- [Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game](https://mlsanity.com/paper/2607.28146/) (2026)

## Abstract (arXiv)

Existing challenges in misinformation exposure and susceptibility vary across demographic groups, as some populations are more vulnerable to misinformation than others. Large language models (LLMs) introduce new dimensions to these challenges through their ability to generate persuasive content at scale and reinforcing existing biases. This study investigates the bidirectional persuasion dynamics between LLMs and humans when exposed to misinformative content. We analyze human-to-LLM influence using human-stance datasets and assess LLM-to-human influence by generating LLM-based persuasive arguments. Additionally, we use a multi-agent LLM framework to analyze the spread of misinformation under persuasion among demographic-oriented LLM agents. Our findings show that demographic factors influence susceptibility to misinformation in LLMs, closely reflecting the demographic-based patterns seen in human susceptibility. We also find that, similar to human demographic groups, multi-agent LLMs exhibit echo chamber behavior. This research explores the interplay between humans and LLMs, highlighting demographic differences in the context of misinformation and offering insights for future interventions.