Hexa: Self-Improving for Knowledge-Grounded Dialogue System

arXiv:2310.06404v3 Announce Type: replace-cross
Abstract: A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e.g., web-search, memory retrieval) with modular approaches. However, data for such steps are often inaccessible compared to those of dialogue responses as they are unobservable in an ordinary dialogue. To fill in the absence of these data, we develop a self-improving method to improve the generative performances of intermediate steps without the ground truth data. In particular, we propose a novel bootstrapping …

abstract arxiv cs.ai cs.cl cs.lg data dialogue however improving intermediate knowledge memory modular ordinary practice responses retrieval search type web