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 1906.01148cs.HCcs.LGstat.ML
收藏

人类-人工智能团队的向后兼容性案例

A Case for Backward Compatibility for Human-AI Teams

University of Washington(华盛顿大学);Microsoft Research(微软研究院);University of Michigan(密歇根大学)

Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, Eric Horvitz

摘要:

人工智能系统正在被部署来支持人类在高风险领域的决策。在许多情况下,人类和人工智能组成一个团队,其中人类在审查人工智能的推断后做出决定。一个成功的合作伙伴关系需要人类对人工智能系统的性能,包括其失败的洞察力。我们研究了在这种情况下更新对AI系统的影响。虽然更新可以提高人工智能的预测性能,但它们也可能导致与用户先前的经验和对人工智能推理的信心不一致的变化,从而损害整体团队的表现。我们引入了AI更新与先前用户体验的兼容性的概念,并提出了研究兼容性在人类-AI团队中的作用的方法。三个高风险领域的实证结果表明,目前的机器学习算法不产生兼容的更新。我们提出了一个重新训练的目标,以提高更新的兼容性,通过惩罚新的错误。该目标提供了性能/兼容性权衡的充分利用,实现了更兼容但更准确的更新。

英文摘要:

AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires that the human develops insights into the performance of the AI system, including its failures. We study the influence of updates to an AI system in this setting. While updates can increase the AI's predictive performance, they may also lead to changes that are at odds with the user's prior experiences and confidence in the AI's inferences, hurting therefore the overall team performance. We introduce the notion of the compatibility of an AI update with prior user experience and present methods for studying the role of compatibility in human-AI teams. Empirical results on three high-stakes domains show that current machine learning algorithms do not produce compatible updates. We propose a re-training objective to improve the compatibility of an update by penalizing new errors. The objective offers full leverage of the performance/compatibility tradeoff, enabling more compatible yet accurate updates.

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。

↑