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 2409.07178cs.HC
收藏

通过提问识别设计问题:探索与大语言模型的角色扮演互动以培养设计提问技能

Identify Design Problems Through Questioning: Exploring Role-playing Interactions with Large Language Models to Foster Design Questioning Skills

Hyunseung Lim, Dasom Choi, Hwajung Hong

AI总结:

本研究探索用LLM驱动的对话智能体开展角色扮演以培养设计新手的提问技能,初步实验发现其能激发提问、降低压力,但易引发过度依赖,据此提出了设计考量与未来方向。

摘要:

识别设计问题是提出合理解决方案的关键步骤,但设计新手由于知识和经验有限,这一过程颇具挑战。提问是一项很有前景的技能,能让学生独立识别设计问题,而非被动学习或依赖教师。本研究探索了借助大语言模型(LLM)驱动的对话智能体(CA)开展角色扮演互动,以培养设计新手的提问技能。我们提出了一个LLM驱动的CA原型,并在真实设计课堂中对16名设计新手开展了初步研究,观察学生与LLM驱动的CA之间的互动。研究结果表明,尽管CA激发了提问行为、降低了提问压力,但也意外导致了学生对LLM回复的过度依赖。我们针对用于培养提问技能的LLM驱动CA提出了设计考量与未来工作方向。

英文摘要:

Identifying design problems is a crucial step for creating plausible solutions, but it is challenging for design novices due to their limited knowledge and experience. Questioning is a promising skill that enables students to independently identify design problems without being passive or relying on instructors. This study explores role-playing interactions with Large Language Model (LLM)-powered Conversational Agents (CAs) to foster the questioning skills of novice design students. We proposed an LLM-powered CA prototype and conducted a preliminary study with 16 novice design students engaged in a real-world design class to observe the interactions between students and the LLM-powered CAs. Our findings indicate that while the CAs stimulated questioning and reduced pressure to ask questions, it also inadvertently led to over-reliance on LLM responses. We proposed design considerations and future works for LLM-powered CA to foster questioning skills.

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。

↑