发表机构
RPTU Kaiserslautern; Linköping University; University of Hertfordshire; Eindhoven University of Technology; Australian National University; University of Cambridge; University of Naples Federico II; Ben-Gurion University of the Negev; The Azrieli National Center for Autism and Neurodevelopment Research（凯泽斯劳滕工业大学; 林雪平大学; 赫特福德大学; 埃因霍温理工大学; 澳大利亚国立大学; 剑桥大学; 那不勒斯费德里科二世大学; 本-古里安大学内盖夫分校; 阿兹列利国家自闭症与神经发育研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对基于LLM的HRI中机器人人格模糊等问题，提出含八个组件的提示设计框架及指南，为HRI研究提供结构化设计与报告辅助，强调提示设计需作为社会技术问题处理。
AI 中文摘要
大语言模型（LLM）越来越多地被用于社交机器人的口头交互中，但人机交互（HRI）中的提示设计仍缺乏明确规范。这导致机器人可能出现幻觉能力、行为边界模糊以及人格误导等问题。本文开发了一种面向基于LLM的机器人的提示设计框架，并引入了包含八个功能组件的结构化提示模板，通过该模板可对机器人行为进行指定、约束和调整。该框架基于对现有基于LLM的HRI研究的综述，并补充了在2025年IEEE RO-MAN会议的Robo-Identity研讨会上收集的HRI专家的调查和讨论数据（样本量N=27）。定性研究结果表明，机器人人格的可读性有限、需要适配用户，且在安全性、欺骗性和治理方面存在强烈的伦理担忧。基于这些发现，我们提出了提示设计指南，并附上概念验证模板，作为HRI研究的结构化设计和报告辅助工具。我们认为，提示设计应被视为一个社会技术问题，而非次要的实现细节，需要明确的能力边界、透明的行为假设以及上下文敏感的保障措施，以支持可靠且可解释的人机交互。
英文摘要
Large language models (LLMs) are increasingly used for verbal interaction in social robots, yet prompt design in human-robot interaction (HRI) remains underspecified. As a result, robots may present hallucinated capabilities, unclear behavioural boundaries, and misleading personas. This paper develops a framework for prompt design in LLM-based robots and introduces a structured prompt template comprising eight functional components through which robot behaviour can be specified, bounded, and adapted. The framework is grounded in a review of prior LLM-based HRI work and complemented by survey and discussion data from HRI experts gathered at the Robo-Identity workshop at IEEE RO-MAN 2025 (N=27). The qualitative findings highlight limited legibility of robot personality, the need for user adaptation, and strong ethical concerns about safety, deception, and governance. Based on these findings, we present prompting guidelines accompanied by proof-of-concept template as a structured design and reporting aid for HRI research. We argue that prompt design should be treated as a socio-technical problem rather than a minor implementation detail, requiring explicit capability boundaries, transparent behavioural assumptions, and context-sensitive safeguards to support reliable and interpretable HRI.
CommentsAccepted for publication at the 35th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2026)
