Noesis：具备自适应并行性与跨知识库语义发现的双向图检索增强生成
Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery
浏览论文内容
中文总结 AI 辅助
本文提出具备自适应并行性与跨知识库语义发现的双向图检索增强生成架构Noesis，通过四种算法解决现有Graph-RAG系统的三类局限，在HotpotQA数据集上超越GraphRAG，实现更优性能。
中文摘要 AI 辅助
基于知识图谱的检索增强生成（Graph-RAG）已成为将大语言模型锚定到特定领域语料库的强大范式。然而现有系统存在持续的局限性：（1）静态分块会碎片化长文档，丢失跨段落语义关联；（2）数据导入管道无法自适应扩展；（3）多领域部署要么采用稀释检索精度的单一知识库，要么需要手动用户路由。本文提出Noesis，一种解耦的Graph-RAG架构，通过四种算法解决上述局限：（a）具备图反馈上下文解析器的双向图遍历，模拟人类随记忆衰减的阅读模式；（b）源自TCP拥塞控制的AIMD并发控制器，实现23倍加速且零内存溢出（OOM）事件；（c）面向MoE模型的领域感知选择性量化方法Moesis，在12GB消费级GPU上实现6.3倍加速；（d）具备运行时结构发现的跨知识库语义路由Mesh，使小型本地模型能够执行多跳跨领域推理。在HotpotQA（1000个问题）数据集上，Noesis达到59.5的精确匹配值（EM）、74.7的F1值，使用35B规模的本地模型进行图构建（而非GPT-4o），超越GraphRAG的精确匹配值达27.8。对193页文档的源文本验证显示，其对独立分块提取无法获取的长程因果边达到90%的精度。
英文摘要
Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-specific corpora. However, existing systems face persistent limitations: (1) static chunking fragments long documents, losing cross-section semantic connections; (2) ingestion pipelines do not scale adaptively; and (3) multi-domain deployments require either a monolithic knowledge base that dilutes retrieval precision or manual user routing. We present Noesis, a decoupled Graph-RAG architecture addressing these limitations through four algorithms: (a) Bidirectional Graph Traversal with a Graph-Feedback Context Resolver simulating human reading with degrading memory; (b) an AIMD Concurrency Controller adapted from TCP congestion control, achieving 23x speedup with zero OOM events; (c) Moesis, domain-aware selective quantization for MoE models achieving 6.3x speedup on 12 GB consumer GPUs; and (d) Mesh, cross-KB semantic routing with runtime structural discovery enabling small on-premises models to perform multi-hop cross-domain reasoning. On HotpotQA (1,000 questions), Noesis achieves 59.5 EM / 74.7 F1, surpassing GraphRAG by +27.8 EM while using a 35B on-premises model for graph construction rather than GPT-4o. Source text verification on a 193-page document confirms 90% precision on long-range causal edges inaccessible to chunk-independent extraction.
发表机构
- Alpha Cogs（阿尔法齿轮公司）
机构由 AI 辅助整理，请以论文原文为准。
