W-RAG: Source-Aware Retrieval for Enterprise Document Generation from Heterogeneous Knowledge Bases

2026-08-22

AI Summary

本文针对企业文档生成中异构知识库的不平衡问题，提出W-RAG框架，通过本体引导检索、局部排序和源级权重调整来优化证据组合。

Abstract

Retrieval-Augmented Generation (RAG) enables large language models to incorporate external knowledge during generation, improving factual grounding and domain adaptability. However, existing RAG pipelines assume that evidence retrieved from multiple repositories can be ranked globally using a single similarity function. While suitable for open-domain retrieval, this assumption breaks down in enterprise document generation, where heterogeneous knowledge bases (such as policies, regulations, technical documentation, and departmental guidelines) serve distinct roles and must be jointly represented in the generated document. As a result, global ranking often produces unbalanced context dominated by a subset of sources, leading to incomplete enterprise drafts. To address this limitation, we propose W-RAG, a source-aware retrieval framework that performs ontology-guided retrieval, local ranking within each knowledge base, and source-level weighting to regulate evidence composition. We further introduce a new dataset for retrieval-grounded enterprise document generation spanning multiple document types and industry domains. Experiments show that standard RAG pipelines struggle on this task, while W-RAG significantly improves document coverage and generation quality.

Problem

• Retrieval-Augmented Generation
• enterprise document generation
• heterogeneous knowledge bases
• global ranking

Innovation

• source-aware retrieval
• ontology-guided retrieval
• local ranking
• source-level weighting