Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRI

Researchers at the Robo-Identity workshop at IEEE RO-MAN 2025 (N=27) found that LLM-based social robots often present hallucinated capabilities and misleading personas due to underspecified prompt design, and proposed a structured prompt template with eight functional components to specify, bound, and adapt robot behavior. The study, released on arXiv (2608.26182v1), emphasizes treating prompt design as a socio-technical problem requiring explicit capability boundaries, transparent behavioral assumptions, and context-sensitive safeguards.

arXiv:2608.26182v1 Announce Type: new Abstract: 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.