arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.09770cs.HCcs.AIcs.CL
收藏

ConvXAI:通过对话提供异构AI解释以支持人机科学写作

ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing

University of Michigan(密歇根大学);Pennsylvania State University(宾夕法尼亚州立大学);Carnegie Mellon University(卡内基梅隆大学)

Hua Shen, Chieh-Yang Huang, Tongshuang Wu, Ting-Hao 'Kenneth' Huang

AI总结:

本文提出对话式XAI原型ConvXAI,基于四项设计原则通过对话为科学写作提供异构AI解释,并在用户研究中验证其优于GUI基线。

摘要:

尽管XAI方法大量涌现,用户仍难以获得所需的AI解释。先前研究表明聊天机器人可作为动态解决方案,但面向实际人类需求的对话式XAI智能体的有效设计仍未得到充分探索。本文聚焦于AI辅助科学写作任务中的对话式XAI。基于人类语言学理论和形成性研究,我们确定了四项设计原则:“多面性”、“可控性”、“混合主动性”、“上下文感知下钻”。我们将这些原则融入交互式原型ConvXAI中,该原型通过对话为科学写作提供异构AI解释。在涉及21名用户的两项研究中,ConvXAI在提升人类感知理解和写作改进方面优于基于GUI的基线。本文进一步讨论了用户在与ConvXAI交互进行科学协作写作时的实际使用模式。

英文摘要:

Despite a surge collection of XAI methods, users still struggle to obtain required AI explanations. Previous research suggests chatbots as dynamic solutions, but the effective design of conversational XAI agents for practical human needs remains under-explored. This paper focuses on Conversational XAI for AI-assisted scientific writing tasks. Drawing from human linguistic theories and formative studies, we identify four design rationales: "multifaceted", "controllability", "mix-initiative", "context-aware drill-down". We incorporate them into an interactive prototype, ConvXAI, which facilitates heterogeneous AI explanations for scientific writing through dialogue. In two studies with 21 users, ConvXAI outperforms a GUI-based baseline on improving human-perceived understanding and writing improvement. The paper further discusses the practical human usage patterns in interacting with ConvXAI for scientific co-writing.

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。

↑