A Multi-party Conversational Social Robot Using LLMs

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we describe our setting and the architecture of our LLM-based dialogue system embodied in a social robot and able to have multi-party conversations. Each component is detailed, and a video of the full system is available with the appropriate components highlighted in real-time. Our system decides when it should take its turn, generates human-like clarification requests when the patient pauses mid-utterance, answers in-domain questions (grounding to the in-prompt knowledge), and responds appropriately to out-of-domain requests (like generating jokes or quizzes).

Original languageEnglish
Title of host publicationHRI '24: Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction
PublisherAssociation for Computing Machinery
Pages1273-1275
Number of pages3
ISBN (Electronic)9798400703232
DOIs
Publication statusPublished - 11 Mar 2024
Event19th Annual ACM/IEEE International Conference on Human-Robot Interaction 2024 - Boulder, United States
Duration: 11 Mar 202415 Mar 2024

Conference

Conference19th Annual ACM/IEEE International Conference on Human-Robot Interaction 2024
Abbreviated titleHRI 2024
Country/TerritoryUnited States
CityBoulder
Period11/03/2415/03/24

Keywords

  • accessibility
  • conversational AI
  • human-robot interaction
  • large language models
  • multi-party dialogue
  • social robots

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A Multi-party Conversational Social Robot Using LLMs'. Together they form a unique fingerprint.

Cite this