AI 辅助决策下人机置信度对齐如何降低学习复杂度
Learning to Decide with AI Assistance under Human-Alignment
AI 导读
一项 arXiv 研究将 AI 辅助的二分类预测与决策问题等价于全反馈的两臂在线上下文学习问题,证明任何学习者的期望遗憾下界为 Ω(√(|H|·|B|·T))。
正文 · 原文
Abstract:It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that decision-makers often struggle to determine when to trust a prediction based solely on this communicated confidence. In this context, recent theoretical and empirical work suggests a positive correlation between the utility of AI-assisted decision-making and the degree of alignment between the AI confidence and the decision-makers' confidence in their own predictions. Crucially, these findings do not yet elucidate the extent to which this alignment influences the complexity of learning to make optimal decisions through repeated interactions. In this paper, we address this question in the canonical case of binary predictions and binary decisions. We first show that this problem is equivalent to a two-armed online contextual learning problem with full feedback, and establish a lower bound of $\Omega (\sqrt{|H| \cdot |B| \cdot T} )$ on the expected regret any learner can attain, where $H$ and $B$ denote the sets of human and AI confidence values. We then demonstrate that, under perfect alignment between AI and human confidence, a learner can attain an expected regret of $O(\sqrt{|H| \cdot T\log T})$ and, when $\sqrt{|H|} = O(\log T)$ and $B$ is countable, a non-trivial generalization of the Dvoretzky-Kiefer-Wolfowitz inequality improves the regret bound to $O(\sqrt{T\log T})$. Taken together, these results reveal that alignment can reduce the complexity of learning to make decisions with AI assistance. Experiments on real data from two different human-subject studies where participants solve simple decision-making tasks assisted by AI models show that our theoretical results are robust to violations of perfect alignment.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2605.12646 [cs.LG] |
| (or arXiv:2605.12646v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.12646 arXiv-issued DOI via DataCite |
Submission history
From: Nina Corvelo Benz [view email]
[v1]
Tue, 12 May 2026 18:42:49 UTC (2,565 KB)
[v2]
Tue, 16 Jun 2026 14:18:11 UTC (2,565 KB)
[v3]
Wed, 18 Nov 2026 09:39:49 UTC (3,413 KB)
来源:arXiv cs.AI · arxiv.org