CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models
This addresses the problem of personalizing conversational agents for users, though it is incremental as it builds on existing LLM capabilities.
The researchers tackled the limitation of fixed personalities in LLM-driven conversational agents by developing CloChat, an interface for customizing agent personas, and found that users formed emotional bonds and engaged in more dynamic dialogues compared to ChatGPT.
Large language models (LLMs) have facilitated significant strides in generating conversational agents, enabling seamless, contextually relevant dialogues across diverse topics. However, the existing LLM-driven conversational agents have fixed personalities and functionalities, limiting their adaptability to individual user needs. Creating personalized agent personas with distinct expertise or traits can address this issue. Nonetheless, we lack knowledge of how people customize and interact with agent personas. In this research, we investigated how users customize agent personas and their impact on interaction quality, diversity, and dynamics. To this end, we developed CloChat, an interface supporting easy and accurate customization of agent personas in LLMs. We conducted a study comparing how participants interact with CloChat and ChatGPT. The results indicate that participants formed emotional bonds with the customized agents, engaged in more dynamic dialogues, and showed interest in sustaining interactions. These findings contribute to design implications for future systems with conversational agents using LLMs.