Reproduce “LLM-assisted Graph-RAG Information Extraction from IFC Data” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sima Iranmanesh, Hadeel Saadany, Edlira Vakaj
Birmingham City University researchers develop a graph-based retrieval-augmented generation (Graph-RAG) system that enables natural language querying of complex Building Information Modeling (IFC) data, translating between plain language questions and graph database queries while maintaining accuracy through LLM-assisted information extraction and response generation.
Key insights
- Graph representation preserves relationships between building components better than traditional approaches
- Few-shot prompting enables accurate translation between natural language and database queries
- LLM post-processing of database results provides contextually appropriate responses
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.