arXiv cs.CL· Rabindra Lamsal, Sisi Zlatanova, Haowen Xu, Yafei Sun, Xuesong Shen·· 13 小时前AI 评分29
IfcLLM：通过关系与图表示互补实现 IFC 模型的自然语言查询
IfcLLM: Natural Language Querying of IFC Models through Complementary Relational and Graph Representations
AI 导读
IfcLLM 框架将关系型与图两种表示结合，按查询类型路由到更合适的后端，由 LLM 智能体通过迭代重试与修正推理整合两者，无需用户介入即可从失败中恢复。在三个 IFC 模型的 30 个查询场景上评测，最佳配置达到 96% 准确率。开放权重 LLM 的结果显示其具备在数据敏感的 AEC 场景本地部署的潜力。
正文 · 原文
Abstract:The Industry Foundation Classes (IFC) standard is central to building data exchange across the lifecycle, from design and construction to facility management and Digital Twin integration. In operational settings, stakeholders increasingly require access to building information without specialist knowledge of IFC's complex, deeply nested schema, motivating natural language interfaces. Existing Large Language Model (LLM)-based querying approaches typically rely on a single data representation, which is not equally suited to attribute retrieval and spatial reasoning. We present IfcLLM, a framework that combines complementary relational and graph representations, routing each query type to the more suitable backend. An LLM agent integrates both through iterative retry-and-refine reasoning, recovering from failures without user input. Evaluated on 30 query scenarios across three IFC models, the top-performing configuration achieved 96% accuracy. Results with open-weight LLMs further demonstrate the potential for local deployment in data-sensitive AEC settings.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.13236 [cs.CL] |
| (or arXiv:2605.13236v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.13236 arXiv-issued DOI via DataCite |
Submission history
From: Rabindra Lamsal [view email]
[v1]
Wed, 13 May 2026 09:24:51 UTC (4,096 KB)
[v2]
Mon, 22 Jun 2026 02:54:53 UTC (3,931 KB)
[v3]
Wed, 21 Oct 2026 23:25:08 UTC (4,381 KB)
来源：arXiv cs.CL · arxiv.org