BEST-KAG: Enhancing Question Answering of Building Engineering Standards with Multimodal Knowledge Graph Modeling and Large Language Model
Summary
This paper introduces BEST-KAG, a multimodal knowledge-driven framework for question answering on building engineering standards, leveraging a multimodal knowledge graph and graph-retrieval-based generation to improve clause-grounded traceability and outperform multiple LLMs.
View Cached Full Text
Cached at: 08/13/26, 03:24 PM
# BEST-KAG: Enhancing Question Answering of Building Engineering Standards with Multimodal Knowledge Graph Modeling and Large Language Model Source: [https://arxiv.org/abs/2608.11244](https://arxiv.org/abs/2608.11244) [View PDF](https://arxiv.org/pdf/2608.11244) > Abstract: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\. ## Submission history From: Jia\-Rui Lin \[[view email](https://arxiv.org/show-email/4b4e144d/2608.11244)\] **\[v1\]**Sun, 2 Aug 2026 10:27:15 UTC \(1,721 KB\)
Similar Articles
Enhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment
MetaKGEnrich is a fully automated pipeline that uses graph metrics to detect knowledge gaps in LLM applications, retrieves web evidence, and improves answer quality by 80-87% across three benchmark datasets.
EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language Models
The paper proposes EGT-KG, a retrieval framework that uses evidence-grounded typed knowledge graphs to enhance scientific question-answering with small language models, showing improved performance over standard RAG methods in experiments.
Travel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge Graphs
This paper proposes a modular pipeline that uses a domain-specific knowledge graph to generate multi-hop QA pairs and fine-tune a reasoning LLM (Qwen3-4B) for the travel domain, achieving 82.4% exact match accuracy, significantly outperforming the baseline.
RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation
This paper introduces RSF-GLLM, a framework that decouples differentiable graph reasoning from LLM generation to address the semantic gap in multi-hop knowledge graph question answering, achieving competitive performance with superior inference efficiency.
KARLA: Knowledge-base Augmented Retrieval for Language Models
KARLA proposes a method for LLMs to query a knowledge base during generation, enabling factual updates without retraining and improving transparency. Experiments show improved factual grounding in both short and long-form generation.