Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogues

Hongru WANG, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, Kam-Fai Wong

Submission Type: Regular Long Paper

Submission Track: Dialogue and Interactive Systems

Submission Track 2: Theme Track: Large Language Models and the Future of NLP

Keywords: knowledge-grounded dialogue system, personalized dialogue system, large lanuage models

TL;DR: A novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating to incorporate multiple knowledge sources and address dependency issue

Abstract: Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple sources and response generation, which allows easy extension to various knowledge sources including the possibility of not using any sources. To study the problem, we construct a personalized knowledge-grounded dialogue dataset Knowledge Behind Persona (KBP), which is the first to consider the dependency between persona and implicit knowledge. Experimental results on the KBP dataset demonstrate that the SAFARI framework can effectively produce persona-consistent and knowledge-enhanced responses.

Submission Number: 2905