arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.16042cs.HCcs.AI
收藏

可解释人工智能如何影响人类表现:显著性图行为后果的系统综述

How explainable AI affects human performance: A systematic review of the behavioural consequences of saliency maps

TUD Dresden University of Technology(德累斯顿工业大学)

Romy Müller

AI总结:

该系统综述通过分析68项用户研究,梳理了显著性图对人类表现的影响及调节因素,发现其效应存在差异且受任务类型等多种条件影响,可为后续用户研究设计提供参考。

摘要:

显著性图能够解释深度神经网络对图像的分类方式,但它们对人类是否真的有用?本次系统综述涵盖68项用户研究,结果发现尽管显著性图可以提升人类表现,但零效应甚至负面效应也相当普遍。为探究哪些因素调节这些效应,研究将实证结果按照与人类任务、AI表现、XAI方法、待分类图像、人类参与者及对照条件相关的若干因素进行梳理。在以图像为核心的任务中,收益出现的频率低于以AI为核心的任务,但效应取决于具体的认知需求。此外,收益通常仅限于以AI为核心任务中AI预测错误的情况,而在以图像为核心的任务中则限于AI预测正确的情况。令人意外的是,与XAI相关的因素影响极小。与图像和人类相关的因素证据有限,且效应高度依赖对照条件。这些发现可为未来用户研究的设计提供支持。

英文摘要:

Saliency maps can explain how deep neural networks classify images. But are they actually useful for humans? The present systematic review of 68 user studies found that while saliency maps can enhance human performance, null effects or even costs are quite common. To investigate what modulates these effects, the empirical outcomes were organised along several factors related to the human tasks, AI performance, XAI methods, images to be classified, human participants and comparison conditions. In image-focused tasks, benefits were less common than in AI-focused tasks, but the effects depended on the specific cognitive requirements. Moreover, benefits were usually restricted to incorrect AI predictions in AI-focused tasks but to correct ones in image-focused tasks. XAI-related factors had surprisingly little impact. The evidence was limited for image- and human-related factors and the effects were highly dependent on the comparison conditions. These findings may support the design of future user studies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑