arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.07773cs.ROcs.AI
收藏

序列决策中的人类建模:基于Human-Aware AI视角的分析

Human-Modeling in Sequential Decision-Making: An Analysis through the Lens of Human-Aware AI

Sorbonne University(索邦大学);CNRS(法国国家科学研究中心);INSERM(法国国家健康与医学研究院);Washington University in St. Louis(圣路易斯华盛顿大学);Colorado State University(科罗拉多州立大学)

Silvia Tulli, Stylianos Loukas Vasileiou, Sarath Sreedharan

AI总结:

本研究回溯阐释了Human-Aware AI的构成,提出该范式以人类建模为核心并可提供交互分类维度,通过综述近三年顶会序列决策领域相关论文,识别了被忽视的研究问题,分析了其社科引用、用户研究情况及所用AI方法。

摘要:

“Human-Aware(人类感知)”已成为描述一类旨在与人类协作、交互的AI系统的热门关键词。尽管使用该标签的研究之间存在出人意料的一致性,但这个术语本身在很大程度上仍未得到清晰理解。在本研究中,我们回溯性地尝试阐释Human-Aware AI系统的构成要素。我们发现,Human-Aware AI是一种以设计为导向的范式,其核心是需要对系统可能交互的人类进行建模。此外,我们还发现该范式为我们提供了直观的维度,可用于理解和归类这些系统与人类之间可能存在的各类交互形式。我们将这些维度作为工具,用于理解和综述声称包含某种形式人类建模的人-AI系统相关研究的当前格局,以此展示这些维度的教学价值。为契合研讨会论文的范围,我们特意将综述范围缩小至过去三年发表在顶级AI会议上、涉及序列决策的论文。我们的分析有助于识别目前被忽视的潜在研究问题空间。我们还额外分析了这些研究明确引用社会科学研究成果的程度,以及它们是否真正开展了用户研究来验证其系统。此外,我们还统计了这些研究使用的各类AI方法。

英文摘要:

"Human-aware" has become a popular keyword used to describe a particular class of AI systems that are designed to work and interact with humans. While there exists a surprising level of consistency among the works that use the label human-aware, the term itself mostly remains poorly understood. In this work, we retroactively try to provide an account of what constitutes a human-aware AI system. We see that human-aware AI is a design oriented paradigm, one that focuses on the need for modeling the humans it may interact with. Additionally, we see that this paradigm offers us intuitive dimensions to understand and categorize the kinds of interactions these systems might have with humans. We show the pedagogical value of these dimensions by using them as a tool to understand and review the current landscape of work related to human-AI systems that purport some form of human modeling. To fit the scope of a workshop paper, we specifically narrowed our review to papers that deal with sequential decision-making and were published in a major AI conference in the last three years. Our analysis helps identify the space of potential research problems that are currently being overlooked. We perform additional analysis on the degree to which these works make explicit reference to results from social science and whether they actually perform user-studies to validate their systems. We also provide an accounting of the various AI methods used by these works.

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。

↑