{"slug": "intelligent-identification-and-repair-of-design-defects-in-bim-via-domain-large", "title": "Intelligent Identification and Repair of Design Defects in BIM via Domain-Specific Large Language Models", "summary": "A new framework using domain-specific large language models (LLMs) identifies and repairs design defects in Building Information Modeling (BIM), achieving 85% identification accuracy versus 70% for traditional rule checking and a 94% rate of reasonable repair suggestions. The framework, proposed in an arXiv paper (2608.28629v1), introduces a BIM-to-Text method with component-balanced chunking, prompt learning with rule injection, few-shot prompting, and retrieval-augmented generation (RAG), plus a hallucination control strategy that increased accuracy from 64% to 85% and eliminated 92.5% of hallucinations in a single intervention round.", "body_md": "arXiv:2608.28629v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/intelligent-identification-and-repair-of-design-defects-in-bim-via-domain-large", "canonical_source": "https://arxiv.org/abs/2608.28629", "published_at": "2026-09-01 04:00:00+00:00", "updated_at": "2026-09-01 04:24:52.314877+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-research"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/intelligent-identification-and-repair-of-design-defects-in-bim-via-domain-large", "markdown": "https://wpnews.pro/news/intelligent-identification-and-repair-of-design-defects-in-bim-via-domain-large.md", "text": "https://wpnews.pro/news/intelligent-identification-and-repair-of-design-defects-in-bim-via-domain-large.txt", "jsonld": "https://wpnews.pro/news/intelligent-identification-and-repair-of-design-defects-in-bim-via-domain-large.jsonld"}}