重新思考检索：从传统检索增强生成到金融领域大语言模型中的代理和非向量推理系统
Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models
AI总结：
本文提出基于向量的代理RAG方法，在金融问答中优于非向量方法，通过交叉编码器重排序和小到大块检索显著提升检索精度和回答质量，但需权衡成本性能。
摘要：
最近在检索增强生成（RAG）方面的进展使大型语言模型能够利用美国证券交易委员会文件、业绩报告和监管文件等外部知识库来回答金融问题。然而，现有研究缺乏对基于向量和非向量RAG架构在金融文档中的系统比较，以及高级RAG技术对检索准确性、回答质量、延迟和成本的实证影响仍不清楚。我们提出了第一个系统评估，比较基于向量的代理RAG使用混合搜索和元数据过滤与不使用嵌入的分层节点系统，后者通过遍历文档结构。我们评估了两种增强技术应用于向量架构：i）交叉编码器重排序用于检索精度，ii）小到大块检索用于上下文完整性。在1,200份SEC 10-K、10-Q和8-K文件上，针对150个问题基准测试，我们测量检索指标（MRR、Recall@5）、通过LLM作为裁判的 pairwise 比较来评估回答质量、延迟和预处理成本。基于向量的代理RAG在具有可比延迟（5.2秒与5.98秒）的情况下，对分层节点系统有68%的胜率。交叉编码器重排序在最优参数（10,5）下实现了59%的绝对提升。小到大检索在仅增加0.2秒延迟的情况下，对基线块检索有65%的胜率。我们的发现表明，将高级RAG技术应用于金融问答系统可以提高检索准确性、回答质量，并且在生产环境中需要考虑成本性能的权衡。
英文摘要：
Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing work lacks systematic comparison of vector-based and non-vector RAG architectures for financial documents, and the empirical impact of advanced RAG techniques on retrieval accuracy, answer quality, latency, and cost remain unclear. We present the first systematic evaluation comparing vector-based agentic RAG using hybrid search and metadata filtering against hierarchical node-based systems that traverse document structure without embeddings. We evaluate two enhancement techniques applied to the vector-based architecture, i) cross-encoder reranking for retrieval precision, and ii) small-to-big chunk retrieval for context completeness. Across 1,200 SEC 10-K, 10-Q, and 8-K filings on a 150-question benchmark, we measure retrieval metrics (MRR, Recall@5), answer quality through LLM-as-a-judge pairwise comparisons, latency, and preprocessing costs. Vector-based agentic RAG achieves a 68% win rate over hierarchical node-based systems with comparable latency (5.2 compared to 5.98 seconds). Cross-encoder reranking achieves a 59% absolute improvement at optimal parameters (10, 5) for MRR@5. Small-to-big retrieval achieves a 65% win rate over baseline chunking with only 0.2 seconds additional latency. Our findings reveal that applying advanced RAG techniques to financial Q&A systems improves retrieval accuracy, answer quality, and has cost-performance tradeoffs to be considered in production.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
