Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting

TL;DR

This paper presents a rapport-building dialogue strategy for virtual agents using large language models, aiming to improve user experience during first meetings through small talk and evaluated via human assessments.

Contribution

It introduces a novel approach combining predefined and free-form dialogue strategies for rapport building in virtual agents, optimized with LLM prompting.

Findings

Free-form prompting yielded higher user satisfaction and engagement.

Rapport score correlated positively with naturalness and satisfaction.

Dialogue strategies improved perceived naturalness and usability.

Abstract

Rapport is known as a conversational aspect focusing on relationship building, which influences outcomes in collaborative tasks. This study aims to establish human-agent rapport through small talk by using a rapport-building strategy. We implemented this strategy for the virtual agents based on dialogue strategies by prompting a large language model (LLM). In particular, we utilized two dialogue strategies-predefined sequence and free-form-to guide the dialogue generation framework. We conducted analyses based on human evaluations, examining correlations between total turn, utterance characters, rapport score, and user experience variables: naturalness, satisfaction, interest, engagement, and usability. We investigated correlations between rapport score and naturalness, satisfaction, engagement, and conversation flow. Our experimental results also indicated that using free-form to prompt the rapport-building strategy performed the best in subjective scores.