Back to Search Start Over

A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation

Authors :
Yang, Chenxu
Lin, Zheng
Tian, Chong
Pang, Liang
Wang, Lanrui
Tong, Zhengyang
Ho, Qirong
Cao, Yanan
Wang, Weiping
Publication Year :
2024

Abstract

Grounding external knowledge can enhance the factuality of responses in dialogue generation. However, excessive emphasis on it might result in the lack of engaging and diverse expressions. Through the introduction of randomness in sampling, current approaches can increase the diversity. Nevertheless, such sampling method could undermine the factuality in dialogue generation. In this study, to discover a solution for advancing creativity without relying on questionable randomness and to subtly reconcile the factuality and diversity within the source-grounded paradigm, a novel method named DoGe is proposed. DoGe can dynamically alternate between the utilization of internal parameter knowledge and external source knowledge based on the model's factual confidence. Extensive experiments on three widely-used datasets show that DoGe can not only enhance response diversity but also maintain factuality, and it significantly surpasses other various decoding strategy baselines.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2407.05718
Document Type :
Working Paper