Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Zhe, Han, Jin, Chen, Ke-Yin, Cao, Xin-Yu, Lu, Xin-Zheng, Lin, Jia-Rui
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909863902183424
author Zheng, Zhe
Han, Jin
Chen, Ke-Yin
Cao, Xin-Yu
Lu, Xin-Zheng
Lin, Jia-Rui
author_facet Zheng, Zhe
Han, Jin
Chen, Ke-Yin
Cao, Xin-Yu
Lu, Xin-Zheng
Lin, Jia-Rui
contents Translating clauses into executable code is a vital stage of automated rule checking (ARC) and is essential for effective building design compliance checking, particularly for rules with implicit properties or complex logic requiring domain knowledge. Thus, by systematically analyzing building clauses, 66 atomic functions are defined first to encapsulate common computational logics. Then, LLM-FuncMapper is proposed, a large language model (LLM)-based approach with rule-based adaptive prompts that match clauses to atomic functions. Finally, executable code is generated by composing functions through the LLMs. Experiments show LLM-FuncMapper outperforms fine-tuning methods by 19% in function matching while significantly reducing manual annotation efforts. Case study demonstrates that LLM-FuncMapper can automatically compose multiple atomic functions to generate executable code, boosting rule-checking efficiency. To our knowledge, this research represents the first application of LLMs for interpreting complex design clauses into executable code, which may shed light on further adoption of LLMs in the construction domain.
format Preprint
id arxiv_https___arxiv_org_abs_2308_08728
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composing
Zheng, Zhe
Han, Jin
Chen, Ke-Yin
Cao, Xin-Yu
Lu, Xin-Zheng
Lin, Jia-Rui
Artificial Intelligence
Computation and Language
Translating clauses into executable code is a vital stage of automated rule checking (ARC) and is essential for effective building design compliance checking, particularly for rules with implicit properties or complex logic requiring domain knowledge. Thus, by systematically analyzing building clauses, 66 atomic functions are defined first to encapsulate common computational logics. Then, LLM-FuncMapper is proposed, a large language model (LLM)-based approach with rule-based adaptive prompts that match clauses to atomic functions. Finally, executable code is generated by composing functions through the LLMs. Experiments show LLM-FuncMapper outperforms fine-tuning methods by 19% in function matching while significantly reducing manual annotation efforts. Case study demonstrates that LLM-FuncMapper can automatically compose multiple atomic functions to generate executable code, boosting rule-checking efficiency. To our knowledge, this research represents the first application of LLMs for interpreting complex design clauses into executable code, which may shed light on further adoption of LLMs in the construction domain.
title Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composing
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2308.08728