KEO：通过知识图谱和RAG进行OMIn的领域知识提取
KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance
AI总结：
KEO通过知识图谱和RAG框架提升航空安全维护中的领域知识提取与推理，实验显示其在全局理解上优于传统文本块RAG，同时保持对细粒度任务的有效性。
摘要：
我们提出了KEO，一种在安全关键情境中使用大语言模型（LLMs）的领域特定知识提取和推理框架。利用Operations and Maintenance Intelligence（OMIn）数据集，我们构建了一个涵盖全球情境理解和可操作维护任务的QA基准。KEO构建了结构化的知识图谱（KG）并将其集成到检索增强生成（RAG）流程中，比传统文本块RAG实现了更连贯的全局推理。我们评估了本地可部署的LLMs（Gemma-3，Phi-4，Mistral-Nemo）并采用更强的模型（GPT-4o，Llama-3.3）作为评判者。实验表明，KEO通过揭示模式和系统级见解显著提升了全局理解，而文本块RAG在需要局部检索的细粒度任务中仍有效。这些发现强调了KG增强LLMs在安全、领域特定问答中的潜力及其在高风险推理中的应用前景。代码可在https://github.com/JonathanKarr33/keo获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
