用知识图谱增强大模型，高效回答通信标准问题
KG2QA: Knowledge Graph-enhanced Retrieval-augmented Generation for Communication Standards Question Answering
- 融合领域知识图谱与微调大模型，通过检索生成提升问答准确性
- 在6587对问答数据上，BLEU-4从18.86提升至66.90，显著优于基线模型
- 适合通信标准研发、测试人员快速查证技术细节
通信技术的快速发展导致标准数量激增，传统依赖专家咨询的方法效率低下。为此，我们提出KG2QA框架，结合微调的大语言模型（LLMs）与领域知识图谱（KG），通过检索增强生成（RAG）管道实现通信标准问答。基于ITU-T建议书构建包含6,587个问答对的高质量数据集，微调Qwen2.5-7B-Instruct模型，使BLEU-4得分从18.86提升至66.90，优于基线模型和Llama-3-8B-Instruct。构建包含13,906个实体和13,524条关系的结构化知识图谱，采用基于自定义本体的LLM辅助三元组抽取。在KG-RAG流程中，微调模型首先从知识图谱中检索相关知识，生成更准确、事实可靠的回复。以DeepSeek-V3为评判标准，系统在五个维度平均得分提升2.26%，展现更强的事实准确性和相关性。系统已集成网页平台与API，支持高效交互。代码与数据已开源：https://github.com/luozhongze/KG2QA。
原文摘要 · Abstract (English)
The rapid evolution of communication technologies has led to an explosion of standards, rendering traditional expert-dependent consultation methods inefficient and slow. To address this challenge, we propose \textbf{KG2QA}, a question answering (QA) framework for communication standards that integrates fine-tuned large language models (LLMs) with a domain-specific knowledge graph (KG) via a retrieval-augmented generation (RAG) pipeline. We construct a high-quality dataset of 6,587 QA pairs from ITU-T recommendations and fine-tune Qwen2.5-7B-Instruct, achieving significant performance gains: BLEU-4 increases from 18.86 to 66.90, outperforming both the base model and Llama-3-8B-Instruct. A structured KG containing 13,906 entities and 13,524 relations is built using LLM-assisted triple extraction based on a custom ontology. In our KG-RAG pipeline, the fine-tuned LLMs first retrieves relevant knowledge from KG, enabling more accurate and factually grounded responses. Evaluated by DeepSeek-V3 as a judge, the KG-enhanced system improves performance across five dimensions, with an average score increase of 2.26\%, demonstrating superior factual accuracy and relevance. Integrated with Web platform and API, KG2QA delivers an efficient and interactive user experience. Our code and data have been open-sourced https://github.com/luozhongze/KG2QA.
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。