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

TL;DR

This paper assesses the ability of large language models to generate natural small talk for social robots, introduces a feedback method to improve responses, and demonstrates enhanced human-like interactions.

Contribution

It presents a novel feedback-driven approach to improve LLM-generated small talk responses for social robots, advancing natural human-robot social interactions.

Findings

System effectively guides LLM responses to be more natural and human-like.

Evaluation shows improved rapport-building in human-robot interactions.

Method enhances the sociability of social robots through better small talk.

Abstract

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.