A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation
This addresses a key challenge in dialogue systems for applications requiring both accurate and engaging responses, though it is an incremental improvement within existing paradigms.
The paper tackles the trade-off between factuality and diversity in knowledge-grounded dialogue generation by proposing DoGe, a method that dynamically alternates between internal and external knowledge based on factual confidence. Experiments on three datasets show it enhances diversity while maintaining factuality, significantly outperforming baseline decoding strategies.
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.