# Argumentative Experience: Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debates

arXiv: https://arxiv.org/abs/2412.04629 · HTML: https://mlsanity.com/paper/2412.04629/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2024.

## Built on by (most cited first, 15 of 15)

- [Creativity in LLM-based Multi-Agent Systems: A Survey](https://mlsanity.com/paper/2505.21116/) (2025)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs](https://mlsanity.com/paper/2505.11556/) (2025)
- [Retrieval-augmented systems can be dangerous medical communicators](https://mlsanity.com/paper/2502.14898/) (2025)
- [Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning](https://mlsanity.com/paper/2512.02914/) (2025)
- [DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal](https://mlsanity.com/paper/2601.18081/) (2026)
- [Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation](https://mlsanity.com/paper/2509.20553/) (2025)
- [Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents](https://mlsanity.com/paper/2602.01405/) (2026)
- [The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models](https://mlsanity.com/paper/2506.16724/) (2025)
- [More Isn't Always Better: Balancing Decision Accuracy and Conformity Pressures in Multi-AI Advice](https://mlsanity.com/paper/2603.22152/) (2026)
- [Reflecti-Mate: A Conversational Agent for Adaptive Decision-Making Support Through System 1 and System 2 Thinking](https://mlsanity.com/paper/2605.22509/) (2026)
- [Alleviating Choice Supportive Bias in LLM with Reasoning Dependency Generation](https://mlsanity.com/paper/2512.03082/) (2025)
- [Exploring Learners' Expectations and Engagement When Collaborating with Constructively Controversial Peer Agents](https://mlsanity.com/paper/2601.13479/) (2026)
- [A Roadmap to Impactful Pluralistic Alignment Research](https://mlsanity.com/paper/2607.22305/) (2026)
- [DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents](https://mlsanity.com/paper/2609.29309/) (2026)

## Abstract (arXiv)

Multi-persona debate systems powered by large language models (LLMs) show promise in reducing confirmation bias, which can fuel echo chambers and social polarization. However, empirical evidence remains limited on whether they meaningfully shift user attention toward belief-challenging content, promote belief change, or outperform traditional debiasing strategies. To investigate this, we compare an LLM-based multi-persona debate system with a two-stance retrieval-based system, exposing participants to multiple viewpoints on controversial topics. By collecting eye-tracking data, belief change measures, and qualitative feedback, our results show that while the debate system does not significantly increase attention to opposing views, or make participants shift away from prior beliefs, it does provide a buffering effect against bias caused by individual cognitive tendency. These findings shed light on both the promise and limits of multi-persona debate systems in information seeking, and we offer design insights to guide future work toward more balanced and reflective information engagement.