研究发现人类能通过辩论修正判断，较弱 AI 模型则不能
Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not
arXiv 论文研究 AI Safety via Debate 协议能否让人类和 LLM 监督者克服先验信念、接近正确答案。结果显示，辩论能提升人类判断者的准确率，而单一专家论证的咨询基线做不到；对较弱语言模型，多数设置下辩论没有带来可比增益，甚至可能降低准确率。多判断者协议中加权投票对人类监督者准确率最高，但对 LLM 无论判断者数量如何增加都无显著提升。
Authors:Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto, Oscar Agustin Stanchi, Guido Ernesto Bergman, Giovanni Franco Gabriel Marrafini, Trinidad Borrell, Guido Freire, Joaquin Salvador Machulsky, Mario Alejandro Leiva, Ana Lopez, Nicolas Spinelli, Luca Nicolas Forziati Gangi, Eitan Sprejer, Federico Barrera Lemarchand, Gerardo Simari, Maria Vanina Martinez
Abstract:How can we effectively oversee AI systems that surpass human intelligence? AI Safety via Debate proposes that two AI systems argue opposing positions and a judge, either a human or a weaker model, decides which is correct. By facilitating supervisors in providing high-quality training signals, debate aims to encourage truthful and safe behavior from AI systems whose capabilities exceed our own. However, human judgment is not neutral: people often rely on biases which advanced AI systems may learn to exploit. Drawing on insights from collective intelligence and social cognition, this paper investigates whether debate can guide human and LLM supervisors toward the truth despite their prior beliefs. We evaluate several protocol configurations. We also explore setups inspired by the wisdom of the crowd such as the number and diversity of judges, as well as interaction mechanisms including deliberation and voting. Overall, we find that debate increases accuracy relative to prior beliefs for human judges, whereas the consultancy baseline, in which a single expert argues for one answer, does not. For weaker language models, however, the results are mixed: debate provides no comparable gains in most settings and can even reduce accuracy. Among multi-judge protocols, weighted voting produces the highest accuracy for human supervisors, whereas for LLMs none of them significantly improves group accuracy, even as the number of judges increases. Notably, the behavior of minority judges in non-diverse deliberation protocols suggests that, under symmetric settings, incorrect positions could be more persuasive than correct ones. These findings support debate as a viable path toward scalable human oversight, but cast doubt on its benefits for weaker AI supervisors, raising concerns about fully automated training and control pipelines in high-stakes settings.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28539 [cs.AI] |
| (or arXiv:2610.28539v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28539 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Denise Alejandra Mester [view email]
[v1]
Tue, 20 Oct 2026 17:10:36 UTC (2,566 KB)
来源：arXiv cs.AI · arxiv.org