ChatGPT Role-play Dataset: Analysis of User Motives and Model Naturalness

TL;DR

This paper introduces a new dataset of human-ChatGPT conversations, analyzing user motives and response naturalness in normal and role-play settings to improve understanding and effectiveness of human-AI interactions.

Contribution

It presents a novel dataset with annotations on user motives and naturalness, and provides insights into conversational dynamics in different interaction contexts.

Findings

Diverse user motives influence interaction patterns.

AI responses vary in naturalness across settings.

The dataset enables targeted improvements in human-AI communication.

Abstract

Recent advances in interactive large language models like ChatGPT have revolutionized various domains; however, their behavior in natural and role-play conversation settings remains underexplored. In our study, we address this gap by deeply investigating how ChatGPT behaves during conversations in different settings by analyzing its interactions in both a normal way and a role-play setting. We introduce a novel dataset of broad range of human-AI conversations annotated with user motives and model naturalness to examine (i) how humans engage with the conversational AI model, and (ii) how natural are AI model responses. Our study highlights the diversity of user motives when interacting with ChatGPT and variable AI naturalness, showing not only the nuanced dynamics of natural conversations between humans and AI, but also providing new avenues for improving the effectiveness of human-AI communication.