More than Chit-Chat: Developing Robots for Small-Talk Interactions

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ramnauth, Rebecca, Brščić, Dražen, Scassellati, Brian
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912168829517824
author Ramnauth, Rebecca
Brščić, Dražen
Scassellati, Brian
author_facet Ramnauth, Rebecca
Brščić, Dražen
Scassellati, Brian
contents Beyond mere formality, small talk plays a pivotal role in social dynamics, serving as a verbal handshake for building rapport and understanding. For conversational AI and social robots, the ability to engage in small talk enhances their perceived sociability, leading to more comfortable and natural user interactions. In this study, we evaluate the capacity of current Large Language Models (LLMs) to drive the small talk of a social robot and identify key areas for improvement. We introduce a novel method that autonomously generates feedback and ensures LLM-generated responses align with small talk conventions. Through several evaluations -- involving chatbot interactions and human-robot interactions -- we demonstrate the system's effectiveness in guiding LLM-generated responses toward realistic, human-like, and natural small-talk exchanges.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18023
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle More than Chit-Chat: Developing Robots for Small-Talk Interactions
Ramnauth, Rebecca
Brščić, Dražen
Scassellati, Brian
Robotics
Artificial Intelligence
Human-Computer Interaction
Beyond mere formality, small talk plays a pivotal role in social dynamics, serving as a verbal handshake for building rapport and understanding. For conversational AI and social robots, the ability to engage in small talk enhances their perceived sociability, leading to more comfortable and natural user interactions. In this study, we evaluate the capacity of current Large Language Models (LLMs) to drive the small talk of a social robot and identify key areas for improvement. We introduce a novel method that autonomously generates feedback and ensures LLM-generated responses align with small talk conventions. Through several evaluations -- involving chatbot interactions and human-robot interactions -- we demonstrate the system's effectiveness in guiding LLM-generated responses toward realistic, human-like, and natural small-talk exchanges.
title More than Chit-Chat: Developing Robots for Small-Talk Interactions
topic Robotics
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2412.18023