Utilizing Large Language Models (LLMs) facilitates the creation of flexible and natural dialogues, a task that has been challenging with traditional rule-based dialogue systems. However, LLMs also have the potential to produce unexpected responses, which may not align with the intentions of dialogue system designers. To address this issue, this paper introduces a meta-control method that employs LLMs to develop more stable and adaptable dialogue systems. The method includes dialogue flow control to ensure that utterances conform to predefined scenarios and turn-taking control to foster natural dialogues. Furthermore, we have implemented a dialogue system that utilizes this meta-control strategy and verified that the dialogue system utilizing meta-control operates as intended.
@article{arxiv.2312.13715,
title = {Meta-control of Dialogue Systems Using Large Language Models},
author = {Kotaro Shukuri and Ryoma Ishigaki and Jundai Suzuki and Tsubasa Naganuma and Takuma Fujimoto and Daisuke Kawakubo and Masaki Shuzo and Eisaku Maeda},
journal= {arXiv preprint arXiv:2312.13715},
year = {2023}
}
Comments
This paper is part of the proceedings of the Dialogue Robot Competition 2023