用假设问题增强文本表示，让检索更精准
QuOTE: Question-Oriented Text Embeddings
- 给文本块附加潜在可回答的问题，丰富语义表征
- 在多跳问答任务中显著提升检索准确率
- 适合需要精准理解用户意图的对话与搜索系统
我们提出QuOTE（Question-Oriented Text Embeddings），一种用于改进检索增强生成（RAG）系统的新型方法，旨在提升文档表示的准确性与细腻度。与传统RAG管道依赖原始文本片段嵌入不同，QuOTE通过为文本片段附加其可能回答的假设性问题，扩展了表征空间。这使文档嵌入更贴近用户查询语义，有效缓解歧义和上下文相关性问题。在多个基准测试中的大量实验表明，QuOTE显著提升了检索准确率，包括多跳问答任务。研究结果凸显了问题生成作为基础索引策略的潜力，为将问题生成整合进基于检索的AI流水线开辟了新路径。
原文摘要 · Abstract (English)
We present QuOTE (Question-Oriented Text Embeddings), a novel enhancement to retrieval-augmented generation (RAG) systems, aimed at improving document representation for accurate and nuanced retrieval. Unlike traditional RAG pipelines, which rely on embedding raw text chunks, QuOTE augments chunks with hypothetical questions that the chunk can potentially answer, enriching the representation space. This better aligns document embeddings with user query semantics, and helps address issues such as ambiguity and context-dependent relevance. Through extensive experiments across diverse benchmarks, we demonstrate that QuOTE significantly enhances retrieval accuracy, including in multi-hop question-answering tasks. Our findings highlight the versatility of question generation as a fundamental indexing strategy, opening new avenues for integrating question generation into retrieval-based AI pipelines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。