不要被愚弄:人机协作中解释的错误信息效应
Don't be Fooled: The Misinformation Effect of Explanations in Human-AI Collaboration
AI总结:
本文通过 n=160 的 AI 辅助决策实验发现,正确建议搭配错误解释会诱发错误信息效应,损害协作绩效及协作后的推理与程序性知识。
摘要:
在各类应用中,人类越来越多地使用黑盒人工智能(AI)系统,却无法洞察这些系统的推理过程。为应对这种不透明性,可解释 AI(XAI)方法承诺提升透明度和可解释性。尽管近期研究已经探讨了 XAI 如何影响人机协作,但很少有人考察错误解释可能造成的隐患。其对人类的影响可能十分深远,却尚未得到广泛研究。为调查这一问题,我们开展了一项关于 AI 辅助决策的研究(n=160),其中人类由 XAI 提供支持。研究结果表明,当正确的 AI 建议伴随错误解释时,会产生错误信息效应,并在协作结束后仍带来影响。该效应导致人类推断出有缺陷的推理策略,从而妨碍任务执行,并表现出程序性知识受损。此外,错误解释还会在协作过程中损害人机团队的绩效。通过本研究,我们为 HCI 作出贡献:提供了错误解释在协作结束后对人类产生负面后果的实证证据,并为 AI 设计者概述了相关指南。
英文摘要:
Across various applications, humans increasingly use black-box artificial intelligence (AI) systems without insight into these systems' reasoning. To counter this opacity, explainable AI (XAI) methods promise enhanced transparency and interpretability. While recent studies have explored how XAI affects human-AI collaboration, few have examined the potential pitfalls caused by incorrect explanations. The implications for humans can be far-reaching but have not been explored extensively. To investigate this, we ran a study (n=160) on AI-assisted decision-making in which humans were supported by XAI. Our findings reveal a misinformation effect when incorrect explanations accompany correct AI advice with implications post-collaboration. This effect causes humans to infer flawed reasoning strategies, hindering task execution and demonstrating impaired procedural knowledge. Additionally, incorrect explanations compromise human-AI team-performance during collaboration. With our work, we contribute to HCI by providing empirical evidence for the negative consequences of incorrect explanations on humans post-collaboration and outlining guidelines for designers of 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。