# AI Debate Aids Assessment of Controversial Claims

arXiv: https://arxiv.org/abs/2506.02175 · HTML: https://mlsanity.com/paper/2506.02175/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2025.

## Built on by (most cited first, 9 of 9)

- [Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team](https://mlsanity.com/paper/2506.14234/) (2025)
- [AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs](https://mlsanity.com/paper/2510.13912/) (2025)
- [When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?](https://mlsanity.com/paper/2510.20963/) (2025)
- [Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification](https://mlsanity.com/paper/2603.28488/) (2026)
- [Locating Hidden Failures Makes Long-Horizon Agents More Reliable](https://mlsanity.com/paper/2609.17930/) (2026)
- [When Can LLMs Learn to Reason with Weak Supervision?](https://mlsanity.com/paper/2604.18574/) (2026)
- [Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation](https://mlsanity.com/paper/2605.15343/) (2026)
- [Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation](https://mlsanity.com/paper/2607.14256/) (2026)
- [Belief Cascades Drive Persuasion in LLM Agent Networks](https://mlsanity.com/paper/2608.25152/) (2026)

## Abstract (arXiv)

As AI grows more powerful, it will increasingly shape how we understand the world. But with this influence comes the risk of amplifying misinformation and deepening social divides-especially on consequential topics where factual accuracy directly impacts well-being. Scalable Oversight aims to ensure AI systems remain truthful even when their capabilities exceed those of their evaluators. Yet when humans serve as evaluators, their own beliefs and biases can impair judgment. We study whether AI debate can guide biased judges toward the truth by having two AI systems debate opposing sides of controversial factuality claims on COVID-19 and climate change where people hold strong prior beliefs. We conduct two studies. Study I recruits human judges with either mainstream or skeptical beliefs who evaluate claims through two protocols: debate (interaction with two AI advisors arguing opposing sides) or consultancy (interaction with a single AI advisor). Study II uses AI judges with and without human-like personas to evaluate the same protocols. In Study I, debate consistently improves human judgment accuracy and confidence calibration, outperforming consultancy by 4-10% across COVID-19 and climate change claims. The improvement is most significant for judges with mainstream beliefs (up to +15.2% accuracy on COVID-19 claims), though debate also helps skeptical judges who initially misjudge claims move toward accurate views (+4.7% accuracy). In Study II, AI judges with human-like personas achieve even higher accuracy (78.5%) than human judges (70.1%) and default AI judges without personas (69.8%), suggesting their potential for supervising frontier AI models. These findings highlight AI debate as a promising path toward scalable, bias-resilient oversight in contested domains.