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.
@article{arxiv.2312.13925,
title = {AsyncMLD: Asynchronous Multi-LLM Framework for Dialogue Recommendation System},
author = {Naoki Yoshimaru and Motoharu Okuma and Takamasa Iio and Kenji Hatano},
journal= {arXiv preprint arXiv:2312.13925},
year = {2023}
}
Comments
This paper is part of the proceedings of the Dialogue Robot Competition 2023