用注意力机制提升文档检索效率，让大模型更懂上下文。
Efficient Document Retrieval with G-Retriever
- 用注意力机制构建子图，兼顾节点与边的语义信息。
- 在WebQSP数据集上表现优于原有方法，准确率略有提升。
- 适合需要精准文档检索的问答系统开发者使用。
文本数据问答因应用广泛而受到广泛关注。近期一种基于检索增强生成（RAG）的方法引入了奖赏收集斯坦纳树（PCST）优化来构建子图，但该方法仅依赖节点属性，导致上下文理解不完整。本文提出一种改进方法，以注意力机制替代PCST进行子图构建，实现更高效且上下文感知的检索。同时，编码节点与边的属性，获得更丰富的图表示。还引入优化的投影层和多头注意力池化，提升与大语言模型（LLMs）的对齐效果。在WebQSP数据集上的实验表明，该方法性能具有竞争力，结果略优于原方法，验证了其在提升问答准确性方面的潜力。
原文摘要 · Abstract (English)
Textual data question answering has gained significant attention due to its growing applicability. Recently, a novel approach leveraging the Retrieval-Augmented Generation (RAG) method was introduced, utilizing the Prize-Collecting Steiner Tree (PCST) optimization for sub-graph construction. However, this method focused solely on node attributes, leading to incomplete contextual understanding. In this paper, we propose an enhanced approach that replaces the PCST method with an attention-based sub-graph construction technique, enabling more efficient and context-aware retrieval. Additionally, we encode both node and edge attributes, leading to richer graph representations. Our method also incorporates an improved projection layer and multi-head attention pooling for better alignment with Large Language Models (LLMs). Experimental evaluations on the WebQSP dataset demonstrate that our approach is competitive and achieves marginally better results compared to the original method, underscoring its potential for more accurate question answering.
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。