BP4ER: Bootstrap Prompting for Explicit Reasoning in Medical Dialogue Generation

arXiv:2403.19414v1 Announce Type: new
Abstract: Medical dialogue generation (MDG) has gained increasing attention due to its substantial practical value. Previous works typically employ a sequence-to-sequence framework to generate medical responses by modeling dialogue context as sequential text with annotated medical entities. While these methods have been successful in generating fluent responses, they fail to provide process explanations of reasoning and require extensive entity annotation. To address these limitations, we propose the method Bootstrap Prompting for Explicit Reasoning in MDG (BP4ER), …

abstract arxiv attention bootstrap context cs.cl dialogue framework generate medical modeling practical prompting reasoning responses text type value