RAGU：一种结合紧凑型领域自适应大语言模型的多步图检索增强生成引擎

摘要

图检索增强生成（GraphRAG）通过结构化知识增强大语言模型，但现有系统采用单次提取方式构建知识图谱，导致实体噪声与检索脆弱性问题。RAGU作为开源模块化GraphRAG引擎，通过将提取与整合分离来解决该问题：实体和关系依次经过两阶段类型化提取、基于DBSCAN的去重、大语言模型摘要生成以及Leiden社区检测。一个关键洞见推动了轻量级提取器的设计：流水线内大语言模型所需的技能——理解、提取、基于上下文的推理——属于语言技能，其能力随模型规模增长弱于事实性世界知识。据此，我们训练了Meno-Lite-0.1——一个针对语言技能优化的7B模型，该模型在知识图谱构建任务中超越Qwen2.5-32B（调和平均数相对提升12.5%），并在英文GraphRAG任务中与其持平。在GraphRAG-Bench（医学领域）上，RAGU在每个事实层级均检索到最完整的上下文（证据召回率最高达0.84，对比≤0.76），并在综合任务中超越HippoRAG2；在多跳事实型问答任务中，HippoRAG2的明显优势被证明主要是答案格式造成的假象。RAGU可通过`pip install graph_ragu`安装，单GPU即可运行，遵循MIT协议开源。源代码已发布在https://github.com/RaguTeam/RAGU，Meno-Lite-0.1模型可从https://huggingface.co/bond005/meno-lite-0.1获取。

English

Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a single extraction pass, producing noisy entities and brittle retrieval. RAGU, an open-source modular GraphRAG engine, addresses this by separating extraction from consolidation: entities and relations pass through two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection. A key insight motivates a compact extractor: the skills an in-pipeline LLM needs - comprehension, extraction, reasoning over context - are language skills that grow only weakly with model size, unlike factual world knowledge. Accordingly, we train Meno-Lite-0.1, a 7B model optimized for language skills, which outperforms Qwen2.5-32B on knowledge-graph construction (+12.5% relative harmonic mean) and matches it on English GraphRAG tasks. On GraphRAG-Bench (Medical), RAGU retrieves the most complete context at every factoid level (evidence recall up to 0.84 vs. leq0.76) and overtakes HippoRAG2 on synthesis tasks; on multi-hop factoid QA, the apparent HippoRAG2 advantage is shown to be largely an answer-format artifact. RAGU is installable via pip install graph_ragu, runs on a single GPU, and is released under MIT. The source code is publicly available at https://github.com/RaguTeam/RAGU, and the Meno-Lite-0.1 model can be obtained from https://huggingface.co/bond005/meno-lite-0.1.

RAGU：一种结合紧凑型领域自适应大语言模型的多步图检索增强生成引擎

RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM

摘要

Support