面向少样本生成内容 grounding 问答对话的结构化思维链提示方法
Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations
AI总结：
本文提出结构化思维链提示方法，将内容 grounding 多轮问答生成任务分解为状态机中的多个专用状态，显著提升智能体对文档的忠实度，并仅用 6 个种子示例合成高质量训练数据，有效增强对话式问答智能体的域外泛化能力。
摘要：
我们提出了一种结构化思维链（SCoT）提示方法，利用预训练大语言模型（LLM）生成内容 grounding 的多轮问答对话。该方法的核心是将复杂任务在状态机中结构化分解为多个状态，使内容阅读和话语生成等不同子任务对应的动作可以在各自专用状态中执行。每个状态利用一组独特的资源，包括提示词以及（可选的）额外工具来增强生成过程。实验结果表明，带有专门用于幻觉抑制状态的 SCoT 提示可将智能体对 grounding 文档的忠实度提升高达 16.8%。当用作训练数据时，我们仅基于 6 个 Wikipedia 种子示例合成的开放域对话能够训练出性能强大的对话式问答智能体；例如，在域外评估中，当目标域金标数据加入我们生成的示例进行扩充后，我们观察到性能提升高达 13.9%。
英文摘要：
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%. When used as training data, our open-domain conversations 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% over target domain gold data when the latter is augmented with our generated examples.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
