使用大型语言模型解释建筑法规
Using Large Language Models for the Interpretation of Building Regulations
AI总结：
本文研究利用 GPT-3.5 等大型语言模型在少样本学习下将建筑法规自动转换为 LegalRuleML，并验证链式思维与自一致性策略对自动化合规检查的支持效果。
摘要：
合规检查是建筑项目的重要组成部分。近年来，建筑信息模型（BIM）在建筑行业的快速普及为自动化合规检查（ACC）创造了更多机会。BIM 能够共享数字建筑设计数据，这些数据可用于对照法律要求进行合规检查，而法律要求通常以自然语言表达，并非面向机器处理。创建适合 ACC 的法律要求的可计算表示是复杂、昂贵且耗时的。大型语言模型（LLMs），例如驱动 OpenAI ChatGPT 的生成式预训练变换器（GPT）、GPT-3.5 和 GPT-4，能够根据用户提示生成逻辑连贯的文本和源代码。这一能力可用于自动将建筑法规转换为语义化和可计算的表示。本文评估了 LLMs 在少样本学习设置下将建筑法规翻译为 LegalRuleML 的性能。通过仅向 GPT-3.5 提供少量翻译示例，它就能学习该格式的基本结构。利用系统提示，我们进一步指定 LegalRuleML 表示，并探索模型中是否存在专家领域知识。此类领域知识可能通过广泛预训练嵌入 GPT-3.5 中，但需要通过细致的语境化加以引出。最后，我们研究了链式思维推理和自一致性等策略是否适用于该用例。随着 LLMs 变得更加复杂，增强的常识、逻辑连贯性以及领域适应手段能够显著支持 ACC，从而实现更高效、更有效的检查流程。
英文摘要：
Compliance checking is an essential part of a construction project. The recent rapid uptake of building information models (BIM) in the construction industry has created more opportunities for automated compliance checking (ACC). BIM enables sharing of digital building design data that can be used for compliance checking with legal requirements, which are conventionally conveyed in natural language and not intended for machine processing. Creating a computable representation of legal requirements suitable for ACC is complex, costly, and time-consuming. Large language models (LLMs) such as the generative pre-trained transformers (GPT), GPT-3.5 and GPT-4, powering OpenAI's ChatGPT, can generate logically coherent text and source code responding to user prompts. This capability could be used to automate the conversion of building regulations into a semantic and computable representation. This paper evaluates the performance of LLMs in translating building regulations into LegalRuleML in a few-shot learning setup. By providing GPT-3.5 with only a few example translations, it can learn the basic structure of the format. Using a system prompt, we further specify the LegalRuleML representation and explore the existence of expert domain knowledge in the model. Such domain knowledge might be ingrained in GPT-3.5 through the broad pre-training but needs to be brought forth by careful contextualisation. Finally, we investigate whether strategies such as chain-of-thought reasoning and self-consistency could apply to this use case. As LLMs become more sophisticated, the increased common sense, logical coherence, and means to domain adaptation can significantly support ACC, leading to more efficient and effective checking processes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
