针对财报文档设计细粒度检索框架，提升金融问答准确率。
FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval
- 基于财务术语和章节结构构建双层索引，实现精准定位
- 在真实财报上使F1最高提升217.6%，优于现有方法
- 适合金融分析、合规审查等高精度场景使用
10-K财报因篇幅长、结构层级复杂及专业术语多，给信息检索带来挑战，标准RAG模型难以有效利用其结构特征。本文提出FinGEAR（金融映射引导增强问答检索）框架，结合财务术语词典（FLAM）、摘要树与问题树双层索引，以及两阶段交叉编码重排序器，使检索更契合披露结构与领域语言。在完整10-K文档上，以与FinQA数据集对齐的查询进行评估，FinGEAR在精确率、召回率、F1和相关性上均实现稳定提升，相比扁平RAG提升最大达56.7%，较图结构RAG提升12.5%，较先前树结构系统提升217.6%。固定阅读器下，下游答案准确率亦显著提高。通过联合建模章节层级与领域词典信号，该框架显著提升检索保真度，为高风险金融分析提供实用基础。
原文摘要 · Abstract (English)
Financial disclosures such as 10-K filings present challenging retrieval problems due to their length, regulatory section hierarchy, and domain-specific language, which standard retrieval-augmented generation (RAG) models underuse. We introduce FinGEAR (Financial Mapping-Guided Enhanced Answer Retrieval), a retrieval framework tailored to financial documents. FinGEAR combines a finance lexicon for Item-level guidance (FLAM), dual hierarchical indices for within-Item search (Summary Tree and Question Tree), and a two-stage cross-encoder reranker. This design aligns retrieval with disclosure structure and terminology, enabling fine-grained, query-aware context selection. Evaluated on full 10-Ks with queries aligned to the FinQA dataset, FinGEAR delivers consistent gains in precision, recall, F1, and relevancy, improving F1 by up to 56.7% over flat RAG, 12.5% over graph-based RAGs, and 217.6% over prior tree-based systems, while also increasing downstream answer accuracy with a fixed reader. By jointly modeling section hierarchy and domain lexicon signals, FinGEAR improves retrieval fidelity and provides a practical foundation for high-stakes financial analysis.
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。