P4IR applies supervised fine-tuning followed by GRPO reinforcement learning to reduce tree edit distance by up to 23.8% and Levenshtein distance by up to 38.6% versus SFT baselines while outperforming several frontier LLMs on code structure and semantics for automated building code compliance.
Zhang, How can ChatGPT help in automated building code compliance checking?, Int
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reinforcement learning to improve large language model-based automated code compliance systems
P4IR applies supervised fine-tuning followed by GRPO reinforcement learning to reduce tree edit distance by up to 23.8% and Levenshtein distance by up to 38.6% versus SFT baselines while outperforming several frontier LLMs on code structure and semantics for automated building code compliance.