用知识图谱增强大模型，提升航空维修领域的全局理解能力
KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance
- 构建航空维修知识图谱并融入检索生成流程
- 在全局推理任务中表现优于传统文本块检索方法
- 适合高安全要求场景下的智能问答与决策支持
我们提出针对航空运维领域的知识抽取与推理框架KEO，基于Operations and Maintenance Intelligence（OMIn）数据集构建涵盖全局理解与可操作维护任务的问答基准。KEO通过构建结构化知识图谱（KG），并将其集成至检索增强生成（RAG）管道，实现比传统文本块RAG更连贯、覆盖全数据集的推理能力。实验评估了本地部署的LLM（Gemma-3、Phi-4、Mistral-Nemo），并使用GPT-4o、Llama-3.3作为评判者。结果表明，KEO在揭示模式与系统级洞察方面显著提升全局理解能力；而文本块RAG在需局部检索的细粒度操作任务中仍具有效性。研究验证了知识图谱增强型LLMs在高安全领域智能问答中的潜力。代码已开源。
原文摘要 · Abstract (English)
We present Knowledge Extraction on OMIn (KEO), a domain-specific knowledge extraction and reasoning framework with large language models (LLMs) in safety-critical contexts. Using the Operations and Maintenance Intelligence (OMIn) dataset, we construct a QA benchmark spanning global sensemaking and actionable maintenance tasks. KEO builds a structured Knowledge Graph (KG) and integrates it into a retrieval-augmented generation (RAG) pipeline, enabling more coherent, dataset-wide reasoning than traditional text-chunk RAG. We evaluate locally deployable LLMs (Gemma-3, Phi-4, Mistral-Nemo) and employ stronger models (GPT-4o, Llama-3.3) as judges. Experiments show that KEO markedly improves global sensemaking by revealing patterns and system-level insights, while text-chunk RAG remains effective for fine-grained procedural tasks requiring localized retrieval. These findings underscore the promise of KG-augmented LLMs for secure, domain-specific QA and their potential in high-stakes reasoning. The code is available at https://github.com/JonathanKarr33/keo.
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。