发表机构
Japan Advanced Institute of Science and Technology (JAIST); Sumitomo Mitsui Finance and Leasing Co., Ltd.（北陆先端科学技术大学院大学; 三井住友融资租赁有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究生成式人工智能工具下设计意图的形成，通过五位设计师设计着陆页英雄板块的过程，以词汇粒度为视角，发现设计师存在词汇振荡，不匹配促使其反思，还定位了人工智能及模糊性的作用。
AI 中文摘要
生成式人工智能设计工具将自然语言提示作为设计的起点，对设计师提出了新的表达要求。我们探讨设计意图如何通过与人工智能的情境交互形成，而非将提示视为预先存在的设计意图的传递。五位有经验的UI/UX设计师使用生成式人工智能工具设计着陆页英雄板块，并通过出声思考和回顾性访谈记录。运用反思性主题分析，以词汇粒度为敏感视角。设计师呈现出词汇振荡，包括从操作特异性回到模糊性。与人工智能输出的不匹配促使设计师重新思考意图，参与方式从指令转向咨询。一条非振荡轨迹表明概念失调是未来研究的暂定边界。我们将人工智能定位为非中立的生成对话者，将模糊性视为设计判断的资源。
英文摘要
The rapid adoption of generative AI tools has created new literacy demands for designers who must verbalize tacit knowledge through natural language prompts. Yet the micro-level cognitive processes by which designers externalize implicit intentions during iterative AI dialogue remain underexplored. This exploratory qualitative study examined five expert designers (11-20 years UI/UX experience, M = 15.4 years) using think-aloud protocols. We identified "Strategic Oscillation" -- experts' intentional return to vague language (Vibe) after progressing toward operational specifications (Code), leveraging AI's probabilistic nature for creative exploration. We observed shifts from "instruction" to "consultation" mode, deep reflection triggered by semantic collisions, and one participant's disengagement revealing conceptual alignment as a tentative boundary condition. We propose the ECRT cycle (Expectation-Collision-Reflection-Transformation) operationalizing the SECI model's "externalization" phase for human-AI collaboration. These findings yield three design patterns for metacognitive support and position AI as a "probabilistic mirror" catalyzing tacit knowledge externalization.
CommentsAuthor's original version (as submitted, February 2026). This article has been accepted for publication in International Journal of Human-Computer Interaction, published by Taylor & Francis
