CAISSON用双视角聚类提升文档检索，让复杂问题回答更准更快。
CAISSON: Concept-Augmented Inference Suite of Self-Organizing Neural Networks
- 用两个自组织映射构建文本+元数据与概念增强的双视图组织结构
- 在多跳金融问答任务中，对多实体查询的准确率显著优于传统RAG
- 适合需要精准长程推理的金融、法律等专业领域应用
我们提出CAISSON，一种新型分层检索增强生成（RAG）方法，将传统单向量搜索转化为多视角聚类框架。其核心是利用双重自组织映射（SOMs），从不同维度组织文档空间：第一视角融合文本与元数据嵌入，第二视角在元数据中注入概念嵌入，从而同时捕捉细粒度语义关系与高层概念模式。这种双视图机制通过整合多角度证据，实现更精细的文档发现。为评估性能，我们构建了SynFAQA框架，用于生成合成金融分析师笔记与问答对，系统测试信息检索能力。借鉴HotPotQA方法设计多步推理问题，每个问题对应一组包含真实答案的笔记，从单一实体查询逐步扩展至涉及多个实体和概念的复杂多跳任务。实验表明，相较于基础与增强版RAG，CAISSON在复杂多实体查询上表现显著提升，同时保持适用于交互式应用的实际响应速度。
原文摘要 · Abstract (English)
We present CAISSON, a novel hierarchical approach to Retrieval-Augmented Generation (RAG) that transforms traditional single-vector search into a multi-view clustering framework. At its core, CAISSON leverages dual Self-Organizing Maps (SOMs) to create complementary organizational views of the document space, where each view captures different aspects of document relationships through specialized embeddings. The first view processes combined text and metadata embeddings, while the second operates on metadata enriched with concept embeddings, enabling a comprehensive multi-view analysis that captures both fine-grained semantic relationships and high-level conceptual patterns. This dual-view approach enables more nuanced document discovery by combining evidence from different organizational perspectives. To evaluate CAISSON, we develop SynFAQA, a framework for generating synthetic financial analyst notes and question-answer pairs that systematically tests different aspects of information retrieval capabilities. Drawing on HotPotQA's methodology for constructing multi-step reasoning questions, SynFAQA generates controlled test cases where each question is paired with the set of notes containing its ground-truth answer, progressing from simple single-entity queries to complex multi-hop retrieval tasks involving multiple entities and concepts. Our experimental results demonstrate substantial improvements over both basic and enhanced RAG implementations, particularly for complex multi-entity queries, while maintaining practical response times suitable for interactive applications.
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。