Metraipolis › archive › dc_2aaa8146cedb

Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRI — arXiv:2608.26182

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.26182
License (as archived): CC0-1.0
Archived: 2026-10-17T14:16:14.383Z
SHA-256 of the archived text: 546318b5d2ceb6b42af06dfd5d4d0913abb5064af2e439ace0935ad395d4aa85
Stable URL of this page: https://metraipolis.com/documento/dc_2aaa8146cedb

How to cite

Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRI — arXiv:2608.26182 — arXiv (en), https://arxiv.org/abs/2608.26182 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2aaa8146cedb (Metraipolis archive dc_2aaa8146cedb, sha256 546318b5d2ceb6b42af06dfd5d4d0913abb5064af2e439ace0935ad395d4aa85)

BibTeX

@misc{dc2aaa8146cedb,
  title = {Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRI — arXiv:2608.26182},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26182},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2aaa8146cedb; sha256 546318b5d2ceb6b42af06dfd5d4d0913abb5064af2e439ace0935ad395d4aa85},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26182. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.26182 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T13:16:53.449Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).