Researchers have developed PermitGPT, a generative AI framework designed to streamline urban construction governance. This system unifies scattered data from municipal and regulatory sources to identify safety hazards, specify permit requirements, and assess community impact. The framework was fine-tuned using three open-weight language models: Gemma-3-1B for efficient inference, Llama-3.2-3B for regulatory-style outputs, and Mistral-7B-Instruct-v0.3 for strong semantic alignment. PermitGPT represents a step towards AI-assisted construction governance, though further evaluation and validation are needed. AI
IMPACT This framework could improve efficiency and safety in urban construction governance by leveraging AI for data analysis and decision support.
RANK_REASON The cluster contains an academic paper detailing a new AI framework and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]
- BERTScore: Evaluating text generation with BERT
- Gemma 3:1B
- Llama 3.2:3b
- Mistral 7B Instruct v0.3
- New York City Department of Buildings
- NYC 311
- Occupational Safety and Health Administration
- PermitGPT
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
