Reporting Guidelines for Large Language Models in Human–Robot Interaction

Dados Bibliográficos

ID22190804
AutoresCynthia Matuszek (0000-0003-1383-8120, University of Maryland, Baltimore County), Tom Williams (0000-0002-7901-4987, Colorado School of Mines), Nick DePalma (0000-0003-0531-743X, Los Angeles Community College District), Ross Mead (0000-0002-5664-4687, IntraMedical Imaging (United States)), Ruchen Wen (0000-0003-1590-1787, University of Maryland, Baltimore County), Eike Schneiders (0000-0002-8372-1684, University of Southampton), Casey Kennington (0000-0001-6654-8966, Boise State University), Alemitu Bezabih (0000-0001-9603-8537, Colorado School of Mines)
Ano2026
Volume15
Fascículo2
Páginas1-24
Data de publicação2026-03-31
Open AccessNão
TipoARTICLE
PeriódicoACM Transactions on Human-Robot Interaction (JOURNAL)
Identificadores do periódicoISSN: 2573-9522 • E-ISSN: 2573-9522
EditoraAssociation for Computing Machinery (ACM) (PUBLISHER)
DOI10.1145/3777552
OpenAlexW4416767381
IdiomaEN
Referências citadas74

The comparatively recent advent of Large Language Models (LLMs) has resulted in a wide array of new capabilities and components relevant to Human–Robot Interaction (HRI) researchers. LLMs are being applied to vision, manipulation, planning, reasoning, learning, and HRI problems, frequently as “Scarecrows,” in which LLMs serve as black box modules integrated into robot architectures for the purpose of quickly enabling full-pipeline solutions. However, despite this explosion of applications, general questions remain about the best ways to incorporate LLMs into robot architectures, appropriate safety and guardrail considerations, and, critically, how to report properly on HRI research that involves LLMs. In this article, we explore the question of reporting guidelines for HRI researchers who utilize Scarecrows in robot architectures. We identify five key stakeholder groups in the HRI research process, discuss what information each group needs from HRI researchers, and identify appropriate mechanisms for conveying that information from HRI researchers to stakeholders either directly or indirectly. We contribute a set of suggested guidelines regarding what information should be included when researchers disseminate information about HRI research that uses LLMs

Dissemination · Human–robot interaction · Information model · Robot · Stakeholder · Artificial Intelligence in Healthcare and Education · Multimodal Machine Learning Applications · Social Robot Interaction and HRI

Ferramentas

Abrir DOIOpen Access