BIM Information Extraction Through LLM-based Adaptive Exploration

• URL: http://arxiv.org/abs/2605.01698v1
• Date: Sun, 03 May 2026 03:40:29 GMT
• Title: BIM Information Extraction Through LLM-based Adaptive Exploration
• Abstract summary: We introduce adaptive exploration, where an agent iteratively executes code to extract information from a BIM model, discovering its structure at runtime instead of assuming it.<n>We evaluate this approach on ifc-bench v2, an open-source BIM question-answering benchmark introduced alongside this work.<n>A factorial ablation across two LLM capability levels and four augmentation strategies shows that adaptive exploration significantly outperforms static query generation across all configurations.
• Score: 0.7829352305480287
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: BIM models provide structured representations of building geometry, semantics, and topology, yet extracting specific information from them remains remarkably difficult. Current approaches translate natural language into structured queries by assuming a fixed data organization (static approach), which BIM heterogeneity eventually invalidates. We address this with a new paradigm, adaptive exploration, where an LLM-based agent iteratively executes code to extract information from a BIM model, discovering its structure at runtime instead of assuming it. We evaluate this approach on ifc-bench v2, an open-source BIM question-answering benchmark introduced alongside this work, comprising 1,027 tasks across 37 IFC models from 21 projects. A factorial ablation across two LLM capability levels and four augmentation strategies shows that adaptive exploration significantly outperforms static query generation across all configurations, regardless of the augmentation strategy. These results indicate that BIM heterogeneity is best addressed at the paradigm level, not by further optimizing static approaches.

Related papers

• Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework [60.82334952881798]
  Protein-Text Question Answering (QA) is crucial for interpreting biological sequences through natural language.<n>We propose 2D-ProteinRAG, a novel framework that empowers Large Language Models (LLMs) to operate within the gold-standard biological research workflow.<n>We show that 2D-Protein consistently achieves state-of-the-art performance, outperforming fine-tuned baselines and other RAG methods.
  arXiv  Detail & Related papers  (2026-05-17T05:03:24Z)
• A Hybrid Framework for Natural Language Querying of IFC Models with Relational and Graph Representations [1.7964861233408138]
  We introduce IfcLLM, a hybrid framework for natural language interaction with IFC-based BIM models.<n>We implement the framework using an open-weight LLM (GPT OSS 120B), supporting reproducible and deployment-oriented.<n>The results show that combining complementary representations with iterative reasoning enables more accessible natural language querying of IFC data.
  arXiv  Detail & Related papers  (2026-05-13T09:24:51Z)
• FABLE: Forest-Based Adaptive Bi-Path LLM-Enhanced Retrieval for Multi-Document Reasoning [2.9863062339019817]
  We present textbfFABLE, a textbfForest-based textbfAdaptive textbfBi-path textbfLLM-textbfEnhanced retrieval framework.
  arXiv  Detail & Related papers  (2026-01-26T04:00:56Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment [24.80531387685099]
  We propose a novel two-stage exemplar selection strategy that achieves a strong balance between efficiency, generalizability, and performance.<n>First, we fine-tune a BERT-based retriever using structure-aware supervision, guiding it to select exemplars that are both semantically relevant and structurally aligned.<n>Then, we enhance the retriever with a plug-in module, which amplifies syntactically meaningful information in the hidden representations.
  arXiv  Detail & Related papers  (2025-08-28T16:04:39Z)
• Domain-Specific Fine-Tuning and Prompt-Based Learning: A Comparative Study for developing Natural Language-Based BIM Information Retrieval Systems [2.686558478755501]
  Natural Language Interface (NLI) systems are increasingly explored as user-friendly tools for information retrieval in Building Information Modeling environments.<n>Despite their potential, accurately extracting BIM-related data through natural language queries remains a persistent challenge.<n>This study presents a comparative analysis of two prominent approaches for developing NLI-based BIM information retrieval systems.
  arXiv  Detail & Related papers  (2025-08-05T08:51:51Z)
• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [80.88654868264645]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework [15.410873298893817]
  We propose Multi-Modal Knowledge-Based Retrieval-Augmented Generation (MMKB-RAG)<n>This framework leverages the inherent knowledge boundaries of models to dynamically generate semantic tags for the retrieval process.<n>Extensive experiments on knowledge-based visual question-answering tasks demonstrate the efficacy of our approach.
  arXiv  Detail & Related papers  (2025-04-14T10:19:47Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• StructGPT: A General Framework for Large Language Model to Reason over Structured Data [117.13986738340027]
  We develop an emphIterative Reading-then-Reasoning(IRR) approach for solving question answering tasks based on structured data. Our approach can significantly boost the performance of ChatGPT and achieve comparable performance against the full-data supervised-tuning baselines.
  arXiv  Detail & Related papers  (2023-05-16T17:45:23Z)
• An ontology-aided, natural language-based approach for multi-constraint BIM model querying [0.0]
  This paper presents a novel ontology-aided semantic to automatically map natural language queries (NLQs) that contain different constraints into computer-readable codes for querying complex BIM models. A case study about the design-checking of a real-world residential building demonstrates the practical value of the proposed approach in the construction industry.
  arXiv  Detail & Related papers  (2023-03-27T11:35:40Z)
• Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation [87.98063273826702]
  We propose a memory imitation meta-learning (MemIML) method that enhances the model's reliance on support sets for task adaptation. A theoretical analysis is provided to prove the effectiveness of our method.
  arXiv  Detail & Related papers  (2022-03-22T12:41:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.