Crafting a Good Prompt or Providing Exemplary Dialogues? A Study of In-Context Learning for Persona-based Dialogue Generation

arXiv:2402.09954v1 Announce Type: cross
Abstract: Previous in-context learning (ICL) research has focused on tasks such as classification, machine translation, text2table, etc., while studies on whether ICL can improve human-like dialogue generation are scarce. Our work fills this gap by systematically investigating the ICL capabilities of large language models (LLMs) in persona-based dialogue generation, conducting extensive experiments on high-quality real human Chinese dialogue datasets. From experimental results, we draw three conclusions: 1) adjusting prompt instructions is the most direct, effective, and …

abstract arxiv classification context cs.cl cs.lg dialogue etc exemplary gap good human human-like in-context learning machine machine translation prompt research studies study tasks translation type work