用图结构提升检索精度，让小模型也能高效回答机构问题
GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings
- 将推理逻辑从生成阶段移到检索层，用图结构整合文档关系
- 在中等规模模型上实现最高20%的问答质量提升
- 适合需要轻量化部署的封闭领域机构使用
检索增强生成（RAG）系统广泛应用于需基于权威文档回答问题的机构场景。在实体密集型领域，信息分散于异构文档中，仅依赖向量检索常导致证据碎片化，并增加推理时的依赖性。本文提出GRACE-RAG，一种受控检索架构，通过图结构增强检索层，将结构化推理提前至离线阶段，消除结构歧义，支持在自托管的轻量级模型上部署，且模型针对封闭领域机构词汇进行校准。在Mistral 24B、GPT OSS 120B和Gemini 2.5 Flash三种模型容量下均实现完整性、深度与前瞻覆盖度的提升，中等规模模型整体质量最高提升达20%，表明检索架构对结构质量的影响超过模型规模，显著降低计算与延迟开销，且不依赖专有系统。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems are widely used in institutional question answering settings where responses must be grounded in authoritative documentation (Gao et al., 2023). In entity-dense domains where relevant information is distributed across heterogeneous documents, vector-only retrieval often produces fragmented evidence and increases dependence on inference-time reasoning (Zhao et al., 2024). This paper introduces GRACE-RAG, a retrieval-governed, graph-augmented RAG architecture that externalizes structural reasoning from the generative stage to a structured retrieval layer, resolving structural ambiguity offline, enabling deployment on self-hosted lightweight models calibrated to closed-domain institutional vocabulary. Experiments across three model capacities: Mistral 24B, GPT OSS 120B, and Gemini 2.5 Flash show consistent improvements in completeness, depth, and anticipatory coverage, with overall quality gains of up to 20% under mid-scale models, indicating that retrieval architecture governs structural quality over model scale, reducing computational and latency footprint without dependence on proprietary systems.
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。