Graph-Guided Unsupervised Knowledge Identification for Dialogue Agents

Anonymous

Paper Type: short - non archival

Keywords: External Knowledge, Dialogue Response Generation, Unsupervised Retrieval, Node2Vec, Document-Dialogue Graph

TL;DR: An unsupervised approach to precisely identify and select relevant external knowledge to improve the accuracy of response generation in dialogues.

Abstract: Dialogue systems that can effectively respond to user queries in a conversational style have become ubiquitous. Large Language Models (LLMs) have been extensively used as a key component in such systems owing to their linguistic capabilities and implicit knowledge. However, such models are prone to hallucinate while generating a response that can be detrimental, particularly in applications where accuracy is critical. While many works have attempted to address the hallucination concern by supplementing external knowledge in the input to the LLMs, most of them rely on supervised labels to train the knowledge identification module. Such labels might often not be available or difficult to obtain at scale. To address this, we propose our method RANKING, which leverages the structure of the external document to obtain a ranked subset of relevant sentences in an unsupervised manner that can be used for response generation. We model the dependencies in the form of a graph between the sentences present in the external document and the utterances till the given point in the dialogue. We demonstrate the efficacy of RANKING on a commonly used document-grounded conversation dataset (Doc2Dial) where it is observed that RANKING enables generating better responses than using the entire document.