Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models

TL;DR

This paper introduces a scalable method for building role-specific open-domain dialogue systems using large-scale language models, focusing on maintaining role consistency and safety without extensive human dialogue data.

Contribution

It proposes an efficient data collection framework leveraging in-context few-shot learning to create role-satisfying dialogue datasets from scratch.

Findings

Models generate few out-of-bounds utterances

Maintains competitive performance on general metrics

Provides a Korean dialogue dataset for future research

Abstract

Recent open-domain dialogue models have brought numerous breakthroughs. However, building a chat system is not scalable since it often requires a considerable volume of human-human dialogue data, especially when enforcing features such as persona, style, or safety. In this work, we study the challenge of imposing roles on open-domain dialogue systems, with the goal of making the systems maintain consistent roles while conversing naturally with humans. To accomplish this, the system must satisfy a role specification that includes certain conditions on the stated features as well as a system policy on whether or not certain types of utterances are allowed. For this, we propose an efficient data collection framework leveraging in-context few-shot learning of large-scale language models for building role-satisfying dialogue dataset from scratch. We then compare various architectures for open-domain dialogue systems in terms of meeting role specifications while maintaining conversational abilities. Automatic and human evaluations show that our models return few out-of-bounds utterances, keeping competitive performance on general metrics. We release a Korean dialogue dataset we built for further research.