CALL FOR PAPER

-

What: HRI 2024 Workshop on “Scarecrows in Oz: LLMs in HRI” -

When: March 11, 2024 -

Where: Boulder, CO, USA (at the HRI 2024 conference) -

Web: https://scarecrows-hri.github.io

—

IMPORTANT DATES: All dates are Mondays and times are Anywhere on Earth (AoE) unless specified otherwise.

-

Jan. 15, 2024: Submission site opens -

Jan. 29, 2024: Paper deadline -

Feb. 05, 2024: Paper deadline DEADLINE EXTENDED -

Feb. 19, 2024: Notification deadline -

Mar. 04, 2024: Camera-ready deadline -

Mar. 11, 2024: Workshop (half-day)

—

OVERVIEW:

In recent years, Large Language Models (LLMs) have become the focus of intense interest in the AI community and their use in interactive robots for academic research and commercial products has had equal interest; however, there do not currently exist guidelines for or categorizations of their use in various application spaces in Human-Robot Interaction (HRI).

This workshop invites academic researchers and industry professionals who are actively using or are interested in using LLMs for HRI, and who can contribute to the development of high-level, community-wide guidelines for how LLMs can fit correctly and defensibly into the future of HRI research and development.

Relevant topics to this workshop will include HRI studies that either directly or indirectly involve LLMs, as well as HRI studies that utilize the idea of “Scarecrows” [1] (i.e. using LLMs to provide placeholder functionality, similar to Wizard-of-Oz studies) within a larger HRI system; however, we also encourage broader questions and contributions regarding how these models should be conceptualized within frameworks for effective, responsible HRI.

[1] Williams, T.; Matuszek, C; Mead, R.; & Depalma, N. (2023) “Scarecrows in Oz: The Use of Large Language Models in HRI”. To appear in ACM Transactions on Human-Robot Interaction. 10.1145/3606261.

—

TOPICS:

We invite research regarding contributions, commentary, and questions about (and combinations of) the following topics of interest:

-

the impact of “stubbing out” software modules as “Scarecrows” (traditionally done with humans in Wizard-of-Oz contexts) by using LLMs when building and testing HRI studies; -

opportunities and applications of LLMs in HRI; -

risks and perils of LLMs in interactive robots; -

reporting guidelines, ethical considerations, or real-world implications of LLMs in HRI; -

safety of LLM-driven interaction and fine-tuned LLMs during interactions with the world or users; and/or -

position or framing papers on the general role of LLMs in HRI.

—

SUBMISSIONS:

Authors are invited to submit short papers of 2-4 pages on the topic of the use of LLMs in HRI; submissions are due by February 05, 2024. Anonymized submissions should be made using the ACM template https://www.acm.org/publications/proceedings-template; Overleaf provides an appropriate template https://www.overleaf.com/latex/templates/acm-conference-proceedings-primary-article-template/wbvnghjbzwpc that may be used. Submissions will be made through EasyChair https://easychair.org/conferences/?conf=sohri24.

—

MORE INFO:

For more information, please visit our website ( https://scarecrows-hri.github.io) or contact the organizers ( h***************s@gmail.com).

—

ORGANIZERS:

-

Nick DePalma (Semio Community) -

Cynthia Matuszek (University of Maryland, Baltimore County) -

Ross Mead (Semio) -

Tom Williams (Colorado School of Mines) -

Ruchen (Puck) Wen (University of Maryland, Baltimore County)