Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models

Dialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline. Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response generation data, making it costly to transfer. To tackle this challenge, this paper proposed a retrieval-free approach, KiDG, by automatically turning knowledge documents into simulated multi-turn dialogues through a Multi-Document Traversal algorithm. The simulated knowledge-intensive dialogues constructed by KiDG in one domain can be easily used to train and enhance pre-trained dialogue models' knowledge w.r.t. this domain without costly annotation. We conduct extensive experiments comparing retrieval-augmented models and a variety of retrieval-free models. We found that dialogue models enhanced with data simulated with KiDG largely outperform state-ofthe-art retrieval-free methods, and it achieves comparable performance compared to retrievalaugmented methods while being better, and cheaper at domain transfer. We have released the code and data at https://github.com/ DevoAllen/KiDG . * This work was done during the internship at Huawei Recently, Dai et al. (2022) proposed dialogue inpainting to automatically transform a single document into a multi-turn dialogue. However, dialogue data produced by the existing inpainting approach only considers sentences from the same 6608