用领域大模型自动识别修复BIM设计缺陷，准确率超传统方法。
Intelligent Identification and Repair of Design Defects in BIM via Domain-Specific Large Language Models
- 将BIM数据转为文本并分块，适配大模型处理
- 识别准确率达85%，修复建议合理率94%
- 控制幻觉效果显著，适合建筑行业智能化升级
现有方法缺乏通用高效手段来识别和解决BIM中多样的设计缺陷。为此，本文提出一个基于领域特定大语言模型的集成框架，实现BIM缺陷的识别与修复。首先，引入组件平衡分块的BIM-to-Text方法，打通BIM数据与大模型的桥梁；其次，采用规则注入提示学习、少样本提示和RAG技术，实现缺陷识别与修复建议生成；同时，提出结合关键标识符验证与词元长度阈值的幻觉控制策略，确保输出可靠性。实验表明，能力扩展后识别准确率达85%，较传统规则检查提升15个百分点；修复建议合理率达94%。此外，幻觉控制策略将准确率从64%提升至85%，单轮干预消除92.5%的幻觉。本研究构建了从原始BIM数据输入到缺陷识别、修复建议生成的端到端原型系统。
原文摘要 · Abstract (English)
Existing methods lack a generalized approach to efficiently identify and resolve the diversity of design defects in BIM. Therefore, this study proposes an integrated framework to identify and repair various defects in BIM via domain-specific LLMs. Firstly, a BIM-to-Text method with component-balanced chunking is introduced to bridge BIM data with LLMs. Then, prompt learning with rule injection, few-shot prompting and RAG is proposed to identify defects and generate repair suggestions. Meanwhile, a hallucination control strategy combining key identifier validation and token-length thresholds is introduced to ensure reliability. Experiments show capability expansion yields 85% identification accuracy versus 70% for traditional rule checking, achieving a 94% rate of reasonable repair suggestions. Moreover, the proposed hallucination control further increased accuracy from 64% to 85%, eliminating 92.5% of hallucinations in a single intervention round. This study establishes an end-to-end prototype from raw BIM data input, through defect identification, to repair suggestion generation.
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。