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 2407.09516cs.HC
收藏

一种面向可解释人工智能的可操作性评估工具

An Actionability Assessment Tool for Explainable AI

Ronal Singh, Tim Miller, Liz Sonenberg, Eduardo Velloso, Frank Vetere, Piers Howe, Paul Dourish

AI总结:

针对可解释AI中可操作性概念模糊、相关论断缺乏依据的问题,研究人员构建了含7个问题的可操作性评估工具,经两项用户研究验证其可区分不同解释的可操作性且符合人类判断,为该领域提供了首个以人为本的可操作性评估定义与工具。

摘要:

本文介绍并评估了一款供研究人员与从业者使用的工具,用于评估向用户提供的、支持算法追索的信息的可操作性。尽管从用户角度看追索权有明确益处,但可解释人工智能研究中的可操作性概念仍较为模糊,所谓“可操作”的可解释性技术的相关论断均基于研究人员的直觉。受其他领域评估可操作性的定义与工具启发,我们构建了一个包含7个问题的工具,并通过两项用户研究评估其有效性。结果表明,该工具可区分不同解释类型的可操作性,且区分结果与人类判断一致。我们还发现语境对可操作性评估存在影响,表明针对特定领域调整工具或能推动更以人为本的算法系统发展。这是可操作可解释性与算法追索研究及实践的重要进展,首次为可解释人工智能领域的可操作性评估提供了清晰的以人为本的定义与工具。

英文摘要:

In this paper, we introduce and evaluate a tool for researchers and practitioners to assess the actionability of information provided to users to support algorithmic recourse. While there are clear benefits of recourse from the user's perspective, the notion of actionability in explainable AI research remains vague, and claims of `actionable' explainability techniques are based on the researchers' intuition. Inspired by definitions and instruments for assessing actionability in other domains, we construct a seven-question tool and evaluate its effectiveness through two user studies. We show that the tool discriminates actionability across explanation types and that the distinctions align with human judgements. We show the impact of context on actionability assessments, suggesting that domain-specific tool adaptations may foster more human-centred algorithmic systems. This is a significant step forward for research and practices into actionable explainability and algorithmic recourse, providing the first clear human-centred definition and tool for assessing actionability in explainable AI.

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。

↑