Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations

TL;DR

This paper introduces MUCA, a novel LLM-based framework for multi-user group conversations, addressing complexities like timing, content, and participant targeting, and demonstrates its effectiveness through simulations and user studies.

Contribution

The paper presents MUCA, a comprehensive framework with modules for managing multi-user conversations, and introduces MUS for faster optimization and development.

Findings

MUCA effectively manages response timing and content relevance.

MUCA improves user engagement in group discussions.

The MUS accelerates MUCA's development process.

Abstract

Recent advancements in large language models (LLMs) have provided a new avenue for chatbot development. Most existing research, however, has primarily centered on single-user chatbots that determine "What" to answer. This paper highlights the complexity of multi-user chatbots, introducing the 3W design dimensions: "What" to say, "When" to respond, and "Who" to answer. Additionally, we proposed Multi-User Chat Assistant (MUCA), an LLM-based framework tailored for group discussions. MUCA consists of three main modules: Sub-topic Generator, Dialog Analyzer, and Conversational Strategies Arbitrator. These modules jointly determine suitable response contents, timings, and appropriate addressees. This paper further proposes an LLM-based Multi-User Simulator (MUS) to ease MUCA's optimization, enabling faster simulation of conversations between the chatbot and simulated users, and speeding up MUCA's early development. In goal-oriented conversations with a small to medium number of participants, MUCA demonstrates effectiveness in tasks like chiming in at appropriate timings, generating relevant content, and improving user engagement, as shown by case studies and user studies.