AsyncMLD: Asynchronous Multi-LLM Framework for Dialogue Recommendation System

TL;DR

AsyncMLD introduces an asynchronous multi-LLM framework for dialogue systems, enhancing response effectiveness and speed by parallelizing database searches and user intention understanding during speech output.

Contribution

It presents a novel asynchronous framework that improves dialogue response efficiency by parallelizing LLM tasks during speech, addressing latency issues in human-support dialogue agents.

Findings

Reduced response latency in dialogue systems

Improved accuracy in understanding user intent

Enhanced efficiency in database search during speech output

Abstract

We have reached a practical and realistic phase in human-support dialogue agents by developing a large language model (LLM). However, when requiring expert knowledge or anticipating the utterance content using the massive size of the dialogue database, we still need help with the utterance content's effectiveness and the efficiency of its output speed, even if using LLM. Therefore, we propose a framework that uses LLM asynchronously in the part of the system that returns an appropriate response and in the part that understands the user's intention and searches the database. In particular, noting that it takes time for the robot to speak, threading related to database searches is performed while the robot is speaking.