The outstanding performance capabilities of large language model have driven the evolution of current AI system interaction patterns. This has led to considerable discussion within the Human-AI Interaction (HAII) community. Numerous studies explore this interaction from technical, design, and empirical perspectives. However, the majority of current literature reviews concentrate on interactions across the wider spectrum of AI, with limited attention given to the specific realm of interaction with LLM. We searched for articles on human interaction with LLM, selecting 110 relevant publications meeting consensus definition of Human-AI interaction. Subsequently, we developed a comprehensive Mapping Procedure, structured in five distinct stages, to systematically analyze and categorize the collected publications. Applying this methodical approach, we meticulously mapped the chosen studies, culminating in a detailed and insightful representation of the research landscape. Overall, our review presents an novel approach, introducing a distinctive mapping method, specifically tailored to evaluate human-LLM interaction patterns. We conducted a comprehensive analysis of the current research in related fields, employing clustering techniques for categorization, which enabled us to clearly delineate the status and challenges prevalent in each identified area.

翻译：大型语言模型卓越的性能表现推动了当前AI系统交互模式的演进，这引发了人机交互（HAII）领域内的广泛讨论。已有诸多研究从技术、设计和实证视角探索这种交互行为。然而，现有文献综述大多聚焦于更广泛AI领域内的交互形态，对LLM特异性交互领域的关注相对有限。我们检索了人类与LLM交互的相关文献，筛选出110篇符合人机交互共识定义的相关出版物。继而开发了一套涵盖五个不同阶段的综合性映射规程，对收录文献进行系统分析与分类。通过应用这一方法论，我们细致绘制了所选研究的图谱，最终形成对研究图景的详尽真知呈现。总体而言，本综述提出了一种创新方法，引入专门用于评估人类-LLM交互模式的独特映射框架。我们采用聚类技术对相关领域的现有研究进行归类分析，清晰勾勒出各领域的研究现状与面临的挑战。