XAI能提升人机决策表现，但解释本身不是关键因素。
The Effect of Explainable AI-based Decision Support on Human Task Performance: A Meta-Analysis
- 通过元分析整合多篇实验研究，评估XAI对人类决策的影响。
- 使用XAI支持时，任务表现平均提升18.3%，但解释类型影响微弱。
- 研究质量（偏倚风险）是影响效果的关键调节变量，适合关注人机协作的开发者参考。
人工智能输出的可解释性在信息系统中备受关注，推动了对透明性的需求。为此，可解释人工智能（XAI）提出了通过解释AI结果来辅助人类决策的方法。然而，现有实证研究对这类解释是否能提升用户在决策支持系统（DSS）中的任务表现存在不一致结论。本文开展一项元分析，探究XAI对分类任务中人类表现的影响。结果表明，基于XAI的决策支持确实提升了任务表现，但解释本身并非决定性因素。分析显示，研究的偏倚风险显著调节了解释的效果，而解释类型的作用几乎可以忽略。本研究为人机交互领域提供了关于人类与XAI协作机制的深入理解。
原文摘要 · Abstract (English)
The desirable properties of explanations in information systems have fueled the demands for transparency in artificial intelligence (AI) outputs. To address these demands, the field of explainable AI (XAI) has put forth methods that can support human decision-making by explaining AI outputs. However, current empirical works present inconsistent findings on whether such explanations help to improve users' task performance in decision support systems (DSS). In this paper, we conduct a meta-analysis to explore how XAI affects human performance in classification tasks. Our results show an improvement in task performance through XAI-based decision support, though explanations themselves are not the decisive driver for this improvement. The analysis reveals that the studies' risk of bias moderates the effect of explanations in AI, while the explanation type appears to play only a negligible role. Our findings contribute to the human computer interaction field by enhancing the understanding of human-XAI collaboration in DSS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。