维恩图提示：利用脚手架效应加速理解
Venn Diagram Prompting : Accelerating Comprehension with Scaffolding Effect
- Palo Alto Networks（帕洛阿尔托网络公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出维恩图提示技术，通过单次LLM调用替代多步骤策略，消除位置偏差并提升多文档问答一致性，在四个基准数据集上达到或超过精心设计的指令提示性能。
AI中文摘要：
我们提出维恩图（VD）提示，这是一种创新的提示技术，使大型语言模型（LLMs）能够在知识密集型问答任务中，对复杂、多样且长上下文的文档进行信息组合与综合。从多个文档生成答案涉及众多步骤，以提取相关且独特的信息，并将其融合为连贯的回答。为了提高最终答案的质量，通常需要多次调用LLM或使用预训练模型来执行摘要、重组和定制等不同任务。本文所介绍的方法侧重于通过使用VD提示的单次LLM调用来替代多步骤策略。我们提出的技术还旨在消除LLM中固有的位置偏差，通过消除对输入信息顺序的敏感性来增强答案的一致性。它克服了传统上与不同输入序列相关的不一致性问题。基于对提示结果的考察，我们还探讨了VD提示的实际应用。在四个公开基准问答数据集上进行的实验中，VD提示持续达到或超过精心设计、遵循最佳指南和实践的指令提示的性能。
英文摘要：
We introduce Venn Diagram (VD) Prompting, an innovative prompting technique which allows Large Language Models (LLMs) to combine and synthesize information across complex, diverse and long-context documents in knowledge-intensive question-answering tasks. Generating answers from multiple documents involves numerous steps to extract relevant and unique information and amalgamate it into a cohesive response. To improve the quality of the final answer, multiple LLM calls or pretrained models are used to perform different tasks such as summarization, reorganization and customization. The approach covered in the paper focuses on replacing the multi-step strategy via a single LLM call using VD prompting. Our proposed technique also aims to eliminate the inherent position bias in the LLMs, enhancing consistency in answers by removing sensitivity to the sequence of input information. It overcomes the challenge of inconsistency traditionally associated with varying input sequences. We also explore the practical applications of the VD prompt based on our examination of the prompt's outcomes. In the experiments performed on four public benchmark question-answering datasets, VD prompting continually matches or surpasses the performance of a meticulously crafted instruction prompt which adheres to optimal guidelines and practices.
