AI 中文总结
本研究提出BEST-KAG框架，通过多模态知识图谱建模与大语言模型，解决建筑工程标准问答的现有局限，在相关评估指标上优于主流大语言模型。
AI 中文摘要
建筑标准对建筑安全与可持续性至关重要。现有标准应用工作流程依赖基于关键词的文档检索及人工跨条款解读，无法可靠支持多条款推理、多模态知识利用或可追溯的条款级证据关联。为解决这些局限，本研究开发了一个名为BEST-KAG（建筑工程标准的知识增强生成）的多模态知识驱动框架，用于标准知识问答。该框架包含三部分：1）多模态知识图谱（MKG），用于统一表示文档层级及带有各类关联的异构标准知识；2）规则-LLM混合知识构建流水线，用于可扩展的多模态知识抽取，构建了包含251项建筑工程标准、171652个节点和310914条边的大规模多模态知识图谱（MAG）；3）基于图检索的知识增强生成架构，用于基于条款且可追溯的问答。实验表明，在专家评估及BLEU、ROUGE等指标上，BEST-KAG始终优于多个主流大语言模型，与基线相比最佳提升达74.01%。
英文摘要
Construction standards are critical for building safety and sustainability. Existing standard application workflows rely on keyword-based document retrieval and manual cross-clause interpretation, which cannot reliably support multi-clause reasoning, multimodal knowledge utilization, or traceable clause-level evidence linkage. To address these limitations, this study develops a multimodal knowledge-driven framework that supports question answering on standard knowledge named BEST-KAG (Knowledge-Augmented Generation for Building Engineering STandards). The framework introduces 1) a multimodal knowledge graph (MKG) for unified representation of document hierarchy and heterogeneous standard knowledge with various connections, 2) a rule-LLM hybrid knowledge construction pipeline for scalable multimodal knowledge extraction, creating a large MAG with 251 building engineering standards, 171,652 nodes and 310,914 edges, and 3) a graph-retrieval-based knowledge-augmented generation architecture for clause-grounded and traceable question answering. Experiments demonstrate that BEST-KAG consistently outperforms multiple mainstream LLMs in terms of Expert evaluation, and metrics including BLEU, and ROUGE, with the best improvement up to 74.01% compared to the baselines.
