AsyncMLD: Asynchronous Multi-LLM Framework for Dialogue Recommendation System

概要

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.

引用情報

Naoki Yoshimaru, Motoharu Okuma, Takamasa Iio, Kenji Hatano, AsyncMLD: Asynchronous Multi-LLM Framework for Dialogue Recommendation System, Proceedings of the Dialogue Robot Competition 2023, Vol.arXiv:2312.13925, 2023-12-22, DOI: 10.48550/arXiv.2312.13925.