同济大学学报（自然科学版）2025，Vol.53Issue(6)：831-840,10.DOI:10.11908/j.issn.0253-374x.24358
土木工程专业知识驱动大语言模型构建与评测体系
Construction and Evaluation Framework of Large Language Models Driven by Civil Engineering Domain Knowledge
摘要
Abstract
To address the limitations of general large language models(LLMs)in the field of civil engineering due to a lack of specialized knowledge,this study proposes a large knowledge model specifically designed for civil engineering,named CivilGPT.The development of CivilGPT follows a multi-step technical approach,including data preprocessing,the construction of a domain-specific knowledge graph,the generation and optimization of automated datasets,staged pre-training and fine-tuning,and alignment with engineering tasks to ensure that the model can accurately express and reason within the field of civil engineering.Additionally,this study introduces a standardized evaluation framework,Civil-Bench,based on civil engineering qualification exams.Civil-Bench encompasses 13 categories of professional engineering exam questions,including 14,823 objective questions and 269 subjective questions.Testing across 15 domestic and international language models demonstrates that CivilGPT exhibits significant advantages in civil engineering knowledge comprehension,reasoning ability,and solving complex problems.The outcomes of this research lay a technical foundation for the intelligent advancement of the civil engineering field and provide valuable insights for the development of models in other specialized domains.关键词
土木工程/大语言模型/CivilGPT/领域知识图谱/Civil-Bench评测框架Key words
civil engineering/large language model/CivilGPT/domain-specific knowledge graph/Civil-Bench evaluation framework分类
水利科学引用本文复制引用
周颖,孟诗乔,徐灏然,冷皓..土木工程专业知识驱动大语言模型构建与评测体系[J].同济大学学报（自然科学版）,2025,53(6):831-840,10.基金项目
国家重点研发计划(2023YFC3805000) （2023YFC3805000）
国家杰出青年科学基金(52025083) （52025083）
科学探索奖(XP202342) （XP202342）
上海市经信委项目(202201033) （202201033）
