arXiv cs.AI· Andrea Campagner, Federico Cabitza, Vincenzo Crupi·· 12 小时前AI 评分38
人类与机器何时才能真正互补？人机协同的形式条件与实证证据
When Do Humans and Machines Truly Complement Each Other? Formal Conditions and Empirical Evidence for Human-AI Synergy
AI 导读
一篇 arXiv 论文提出用“依赖模式”刻画人类与算法决策的联合正确性结构，并推导出人机协同的数学充要条件：协同能否出现，取决于任一方能否识别并纠正对方的错误，即“人类纠正”与“算法纠正”。基于七项临床案例的分析显示存在“支配陷阱”——算法优势过强反而会削弱人类的纠正性干预、抑制协同；而只要人机错误在功能上不相关，即使存在自动化偏差等认知偏差，协同仍可维持。
正文 · 原文
Abstract:Can humans and artificial intelligence cooperate such that their combination yields greater accuracy than either agent alone? This result, termed \emph{synergy} or \emph{complementarity}, is notoriously difficult to achieve, even when both agents possess significant independent accuracy. In this paper, we present a formal framework to model human-AI interaction through the lens of reliance patterns, which characterize the joint correctness structure of human and algorithmic decisions. We derive mathematically necessary and sufficient conditions for synergy, demonstrating that its emergence depends on the ability of either agent to identify and correct the errors of the other, what we call Human and Algorithmic Correction. Beyond its theoretical contribution, the proposed framework provides a foundation for the design and evaluation of knowledge-based decision support systems, where interaction policies must dynamically integrate heterogeneous sources of expertise. We demonstrate this through the analysis of seven clinical case studies. Our empirical results reveal a ``dominance trap,'' where a strong algorithmic advantage can paradoxically inhibit synergy by eroding human corrective intervention. We also show that synergy can persist even in the presence of cognitive biases, such as automation bias, provided there is functional de-correlation between human and AI errors. These results provide a formal foundation for key concepts in the human-AI systems literature and offer actionable insights for designing interaction-centric AI systems that foster complementarity.
| Comments: | This work has been submitted to, and is currently under review at, IEEE Transactions on Human-Machine Systems for possible publication. Copyright may be transferred without notice |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27965 [cs.AI] |
| (or arXiv:2610.27965v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27965 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andrea Campagner [view email]
[v1]
Tue, 20 Oct 2026 10:09:59 UTC (110 KB)
来源：arXiv cs.AI · arxiv.org