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 2301.07255cs.HCcs.AI
收藏

理解人类直觉在带解释的人机决策中对依赖程度的作用

Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations

Carnegie Mellon University(卡内基梅隆大学);Microsoft Research(微软研究院)

Valerie Chen, Q. Vera Liao, Jennifer Wortman Vaughan, Gagan Bansal

AI总结:

本研究通过混合方法实验探究人类直觉对带解释的人机决策中AI依赖程度的影响,识别出三类直觉与三条推翻AI预测的路径,解释了两种解释方式的效果差异,为人机决策系统及解释方法的发展指明方向。

摘要:

AI解释常被提及为改善人机决策的一种方式,但实证研究尚未发现解释有效性的一致证据,相反,研究表明当AI系统出错时,解释可能会增加过度依赖。尽管影响决策者对AI支持依赖程度的因素有很多,但一个重要因素是决策者如何协调自身直觉——即基于先验知识、经验或模式识别形成的、用于做出判断的信念或启发式方法——与AI系统提供的信息,以决定何时推翻AI预测。我们开展了一项有声思考的混合方法研究,针对两项预测任务采用两种解释类型(基于特征的和基于实例的),以探究决策者的直觉如何影响其对AI预测和解释的使用,并最终影响其选择何时依赖AI。我们的研究结果识别出三类参与AI预测与解释推理过程的直觉:关于任务结果的直觉、关于特征的直觉,以及关于AI局限性的直觉。在此基础上,我们总结了观察到的三条决策者运用自身直觉并推翻AI预测的路径。我们利用这些路径解释了为何(1)我们使用的基于特征的解释并未改善参与者的决策结果,反而增加了其对AI的过度依赖,以及(2)我们使用的基于实例的解释相较于基于特征的解释提升了决策者的表现,并助力实现人机互补的性能。总体而言,我们的工作为AI决策支持系统与解释方法的进一步发展指明了方向,这类系统与方法可帮助决策者有效运用自身直觉,实现对AI的适度依赖。

英文摘要:

AI explanations are often mentioned as a way to improve human-AI decision-making, but empirical studies have not found consistent evidence of explanations' effectiveness and, on the contrary, suggest that they can increase overreliance when the AI system is wrong. While many factors may affect reliance on AI support, one important factor is how decision-makers reconcile their own intuition -- beliefs or heuristics, based on prior knowledge, experience, or pattern recognition, used to make judgments -- with the information provided by the AI system to determine when to override AI predictions. We conduct a think-aloud, mixed-methods study with two explanation types (feature- and example-based) for two prediction tasks to explore how decision-makers' intuition affects their use of AI predictions and explanations, and ultimately their choice of when to rely on AI. Our results identify three types of intuition involved in reasoning about AI predictions and explanations: intuition about the task outcome, features, and AI limitations. Building on these, we summarize three observed pathways for decision-makers to apply their own intuition and override AI predictions. We use these pathways to explain why (1) the feature-based explanations we used did not improve participants' decision outcomes and increased their overreliance on AI, and (2) the example-based explanations we used improved decision-makers' performance over feature-based explanations and helped achieve complementary human-AI performance. Overall, our work identifies directions for further development of AI decision-support systems and explanation methods that help decision-makers effectively apply their intuition to achieve appropriate reliance on 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。

↑