arXiv · cs.AI · Daehwan Ahn (FHCE Department, University of Georgia), Abdullah Almaatouq (MIT Sloan School of Management, Massachusetts Institute of Technology), Monisha Gulabani (The Wharton School, University of Pennsylvania), Kartik Hosanagar (The Wharton School, University of Pennsylvania) · 12 小时前模型评分32
可解释性与结果反馈如何影响用户对 人工智能（AI，Artificial Intelligence） 的信任
Impact of Model Interpretability and Outcome Feedback on Trust in AI
导读
一项预注册实验（N=1,511）对比了可解释性与结果反馈对用户信任和协作表现的影响，发现可解释性并未带来稳定的信任提升，结果反馈的影响显著更大也更可靠。两种因素对参与者任务表现的改善都较为有限，说明提升信任并不等于同等幅度的表现提升。研究提示，人工智能（AI，Artificial Intelligence） 系统辅助人类表现不能只靠增加对 AI 的信任。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “This paper bridges the gap in Human-Computer Interaction (HCI) research by comparatively assessing the effects of interpretability and outcome feedback on user trust and collaborative performance with AI.”
- “Through novel pre-registered experiments (N=1,511 total participants) using an interactive prediction task, we analyzed how interpretability and outcome feedback influence users' task performance and trust in AI.”
来源：arXiv · cs.AI · arxiv.org