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.
Paper Link: https://openreview.net/forum?id=zQTeSUojkr5
Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)
Copyright Consent Signature (type Name Or NA If Not Transferrable): Sanghwan Bae
Copyright Consent Name And Address: NAVER CLOVA, 95, Jeongjail-ro, Bundang-gu, Seongnam-si, Gyeonggi-do, Republic of Korea
Presentation Mode: This paper will be presented in person in Seattle