Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations

arXiv:2402.11770v1 Announce Type: new
Abstract: We introduce a structured chain-of-thought (SCoT) prompting approach to generating content-grounded multi-turn question-answer conversations using a pre-trained large language model (LLM). At the core of our proposal is a structured breakdown of the complex task into a number of states in a state machine, so that actions corresponding to various subtasks, e.g., content reading and utterance generation, can be executed in their own dedicated states. Each state leverages a unique set of resources including prompts …

abstract arxiv breakdown conversations core cs.cl few-shot language language model large language large language model llm machine prompting question state thought type