.png){kind=icon}
Return
Reliable LLM-driven BIM automation through capability-based multi-dimensional evaluation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.autcon.2026.106910.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Six-capability framework to assess LLM reliability in BIM automation. • 31 BIM tasks tested across component, assembly, and system complexity. • Ten error categories; API misuse was the most common failure (48.3%). • MADM scoring shows reliability: 0.603 (comp.), 0.505 (assem.), 0.489 (sys.). • LLMs are strong in debugging but weak in semantic reasoning and API logic.
Keywords:
LLM reliability
BIM automation
capability framework
multi-dimensional evaluation
API misuse
Journal
IF:
11.5
Papers:
6.3K
Citations:
4.2W
Organization
Cited Papers
ShareSaveShareSaveShareSaveA GPT-Powered Assistant for Real-Time Interaction with Building Information Models.png)
BUILDINGS
OAAI
BUILDINGSIF3.1
OAAIShareSaveShareSaveReal operational labeled data of air handling units from office, auditorium, and hospital buildingsScientific Data
OAAI
Scientific DataIF6.9
OAAIShareSaveOptimizing the Utilization of Generative Artificial Intelligence (AI) in the AEC Industry: ChatGPT Prompt Engineering and DesignCivilEngOAAI
CivilEngIF0
OAAIShareSave
View more