A GPT-Powered Assistant for Real-Time Interaction with Building Information Models
Bibliographic record
Abstract
This study introduces DAVE (Digital Assistant for Virtual Engineering), a Generative Pre-trained Transformer (GPT)-powered digital assistant prototype, designed to enable real-time, multimodal interactions within Building Information Modeling (BIM) environments for updating and querying BIM models using text or voice commands. DAVE integrates directly with Autodesk Revit through Python scripts, the Revit API, and the OpenAI API and utilizes Natural Language Processing (NLP). This study presents (1) the development of a practical AI chatbot application that leverages conversational AI and BIM for dynamic actions within BIM models (e.g., updates and queries) at any stage of a construction project and (2) the demonstration of real-time, multimodal BIM model management through voice or text, which aims to reduce the complexity and technical barriers typically associated with BIM processes. The details of DAVE’s development and system architecture are outlined in this paper. Additionally, the comprehensive process of prototype testing and evaluation including the response time analysis and error analysis, which investigated the issues encountered during system validation, are detailed. The prototype demonstrated 94% success in accurately processing and executing single-function user queries. By enabling conversational interactions with BIM models, DAVE represents a significant contribution to the current body of knowledge.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.019 | 0.006 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".