Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations
CoRR(2024)
摘要
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 and
(optionally) additional tools to augment the generation process. Our
experimental results show that SCoT prompting with designated states for
hallucination mitigation increases agent faithfulness to grounding documents by
up to 16.8
synthesized from only 6 Wikipedia-based seed demonstrations train strong
conversational QA agents; in out-of-domain evaluation, for example, we observe
improvements of up to 13.9
augmented with our generated examples.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要