Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models
This addresses the problem of scalable role-specific dialogue systems for developers, though it is incremental as it builds on existing methods with a focus on data efficiency.
The paper tackles the challenge of building open-domain dialogue systems that maintain consistent roles by proposing a data collection framework using large language models to create role-satisfying datasets from scratch, with results showing few out-of-bounds utterances and competitive performance on general metrics.
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.