Building a Personalized Dialogue System with Prompt-Tuning

TL;DR

This paper presents a method for building personalized dialogue systems using prompt-tuning on large-scale language models, achieving natural, consistent responses with lower computational costs.

Contribution

It introduces prompt-tuning for personalized dialogue systems, reducing training costs while maintaining response quality across languages.

Findings

Prompt-tuning enables personalized responses.

The system performs well in English and Japanese.

Lower computational resources are required compared to fine-tuning.

Abstract

Dialogue systems without consistent responses are not fascinating. In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring consistency. Considering the trend of the rapidly increasing scale of language models, we propose an approach that uses prompt-tuning, which has low learning costs, on pre-trained large-scale language models. The results of automatic and manual evaluations in English and Japanese show that it is possible to build a dialogue system with more natural and personalized responses using less computational resources than fine-tuning.