提出自适应混合检索框架，提升金融法律医疗文档问答准确率
Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents
- 根据查询复杂度动态选择向量、树状或混合检索策略
- 混合框架在跨引用和多段落查询上达0.929分，超越单一方法
- 实测显示树状推理在真实财报中胜出11.7个百分点，适合高精度场景
检索增强生成（RAG）已成为大模型外部知识调用的标准范式。本研究在金融、法律与医学领域评估了三种检索架构：向量RAG、树状推理与提出的自适应混合检索（AHR），并构建四层查询复杂度基准，采用GPT-4作为LLM-judge进行评估。实验表明，树状推理整体得分最高（0.900），但在不同层级表现各异：向量RAG在多文档综合任务（Tier 4）得分为0.900，混合框架在跨引用（0.850）和多段落查询（0.929）上最优。跨引用召回率方面，树状与混合方法达100%，向量搜索为91.7%，揭示关键能力差距。在FinanceBench（150道真实美股10-K/10-Q专家标注题）验证中，树状推理得分为0.938，混合框架0.901，向量RAG为0.821，真实文档下树状与向量的差距扩大至11.7个百分点。结果支持基于查询复杂度与文档结构动态选择检索策略的自适应系统发展。所有代码与数据公开。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. [1] presented the first systematic evaluation comparing vector-based agentic RAG against hierarchical node-based reasoning systems for financial document QA across 1,200 SEC filings, finding vector-based systems achieved a 68% win rate. Concurrently, the PageIndex framework [2] demonstrated 98.7% accuracy on FinanceBench through purely reasoning-based retrieval. This paper extends their work by: (i) implementing and evaluating three retrieval architectures: Vector RAG, Tree Reasoning, and the proposed Adaptive Hybrid Retrieval (AHR) across financial, legal, and medical domains; (ii) introducing a four-tier query complexity benchmark; and (iii) employing GPT-4-powered LLM-as-judge evaluation. Experiments reveal that Tree Reasoning achieves the highest overall score (0.900), but no single paradigm dominates across all tiers: Vector RAG wins on multi-document synthesis (Tier 4, score 0.900), while the Hybrid AHR achieves the best performance on cross-reference (0.850) and multi-section queries (0.929). Cross-reference recall reaches 100% for tree-based and hybrid approaches versus 91.7% for vector search, quantifying a critical capability gap. Validation on FinanceBench (150 expert-annotated questions on real SEC 10-K and 10-Q filings) confirms and strengthens these findings: Tree Reasoning scores 0.938, Hybrid AHR 0.901, and Vector RAG 0.821, with the Tree--Vector quality gap widening to 11.7 percentage points on real-world documents. These findings support the development of adaptive retrieval systems that dynamically select strategies based on query complexity and document structure. All code and data are publicly available.
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。