The construction industry is entering a transformative era driven by the convergence of artificial intelligence (AI) and digitalization. Among the most impactful advancements is the emergence of Large Language Models (LLMs), which are reshaping knowledge work across architecture, engineering, and construction (AEC) domains. This paper presents a comprehensive review of LLM applications in the construction sector, examining their role in design automation, building code compliance, predictive analytics, report generation, sustainability planning, and postconstruction facility management. By synthesizing recent developments from leading research and industry use cases, we analyze the technical underpinnings, practical benefits, and deployment challenges associated with LLMs in construction workflows. The study highlights the importance of domain-specific fine-tuning, integration with legacy systems and BIM platforms, and the ethical implications surrounding accountability, transparency, and data privacy. Furthermore, we outline future directions, including hybrid LLM-BIM frameworks, multimodal design generation, and digital twin integration. The findings underscore that while LLMs are not a replacement for human expertise, they are poised to become indispensable collaborators in enabling faster, smarter, and more inclusive built environment solutions. This review serves as a roadmap for researchers, practitioners, and policymakers seeking to responsibly leverage generative AI in construction innovation.

1. Introduction

The construction industry is undergoing a digital transformation driven by the integration of artificial intelligence (AI), data-driven decision-making, and automation. Among the recent breakthroughs in AI, Large Language Models (LLMs) stand out due to their exceptional capacity to process, understand, and generate human-like text based on large corpora of data. Originally developed for natural language tasks such as translation and summarization, LLMs have rapidly expanded into domain-specific applications, including software development, healthcare, finance, and increasingly, construction and infrastructure planning.

The construction industry faces persistent challenges including project delays, communication bottlenecks among stakeholders, regulatory compliance, cost overruns, and the lack of intelligent decision support tools. Traditional tools such as Building Information Modeling (BIM), Computer-Aided Design (CAD), and Project Management Information Systems (PMIS) have improved aspects of visualization and coordination, but they often fall short in automated reasoning, predictive insight, and adaptive planning.

Recent research indicates that LLMs, when integrated into construction workflows, can assist in automating design compliance, report generation, project forecasting, material selection, and stakeholder communication. These models are not only able to parse technical documentation but also engage in interactive Q&A, generate visual concepts from text prompts, and support multiple languages, enabling seamless coordination across geographically distributed teams.

At the core of LLMs’ success lies their ability to generate semantically rich embeddings and context-aware predictions. However, their deployment in construction is still in its early stages and comes with several challenges such as domain adaptation, ethical concerns related to transparency, and integration with legacy systems.

This paper aims to present a comprehensive review of the current state and future potential of LLMs in the construction industry, covering applications, challenges, and future directions.

2. Background and Theoretical Foundation

The emergence of Large Language Models (LLMs) represents a paradigm shift in artificial intelligence, particularly in the domain of natural language understanding and generation. Built on transformer-based architectures, models such as GPT-4, BERT, ERNIE 3.0, and FLAN-T5 are capable of generating contextually accurate, coherent, and adaptable outputs across various domains.

Within the construction industry, LLM adoption is still evolving but gaining momentum. Construction workflows involve highly specialized terminology and multiple data formats including textual descriptions, technical drawings, and structured specifications.

The introduction of transformer architectures has addressed many challenges by enabling scalable and adaptable model structures. Additionally, techniques such as prompt engineering allow users to interact with AI systems using natural language queries.

Fine-tuning methods like Low-Rank Adaptation (LoRA) have further enhanced domain-specific applications by reducing computational costs. Moreover, multimodal integration enables LLMs to interact with images, CAD models, and GIS data, enhancing their usability in construction workflows.

3. Applications of LLMs in Construction

LLMs are increasingly being used across multiple phases of the construction lifecycle, from design development to project monitoring and sustainability planning.

3.1 Design Automation

LLMs can translate natural language descriptions into actionable design inputs, reducing communication gaps between stakeholders. They can assist in layout generation, zoning compliance, and spatial planning.

3.2 BIM Compliance

LLMs can automate compliance checks by analyzing BIM models and validating them against regulatory codes, reducing manual effort and preventing costly errors.

3.3 Delay Prediction and Project Monitoring

By analyzing unstructured data such as reports and communications, LLMs can identify early signs of delays and provide predictive insights for project managers.

3.4 Automated Report Generation

LLMs can generate structured reports including progress updates, compliance summaries, and technical documentation, improving efficiency and reducing human error.

3.5 Sustainability and Material Optimization

LLMs assist in selecting sustainable materials, analyzing environmental impact, and supporting green building certifications.

3.6 IoT-Driven Maintenance

When integrated with IoT systems, LLMs can provide predictive maintenance insights and real-time diagnostics for building systems.

4. Technical and Organizational Challenges

4.1 Domain-Specific Fine-Tuning

LLMs require fine-tuning on domain-specific datasets, which are often limited and difficult to access in construction environments.

4.2 Privacy and Security Concerns

Construction projects involve sensitive data, and LLM deployment must ensure secure handling of confidential information.

4.3 Multilingual Collaboration

LLMs enable multilingual communication across global teams, but require region-specific training for accuracy.

4.4 Legacy System Integration

Integrating LLMs with existing tools like AutoCAD, Revit, and Primavera remains a major challenge due to system incompatibilities.

5. Ethical and Governance Considerations

5.1 Authorship and Accountability

Human oversight remains essential, as AI-generated outputs must be verified by professionals.

5.2 Transparency and Explainability

LLMs must provide explainable outputs to ensure trust and reliability in decision-making.

5.3 Bias and Fairness

Bias in training data can impact outputs, requiring careful dataset selection and auditing.

5.4 Regulatory Compliance

Regulations must evolve to include AI-assisted workflows and define accountability frameworks.

6. Future Directions

Future developments include multimodal LLMs, hybrid LLM-BIM systems, digital twin integration, and AI-driven risk management tools.

7. Conclusion

LLMs are transforming the construction industry by enhancing efficiency, collaboration, and decision-making. While challenges remain, their potential to reshape construction workflows is significant.

Successful adoption will depend on balancing automation with human expertise, ensuring ethical governance, and integrating AI systems into existing infrastructure.

8. References

1. Zhang, Y., et al. (2024). LLM-Driven BIM Compliance in High-Rise Design.

2. Liu, H., et al. (2024). Predicting Construction Delays via LLMs.

3. Zhou, L., et al. (2024). Automated Report Generation in Infrastructure Projects.

4. Wang, J., & Chen, T. (2024). Code Compliance Automation Using ERNIE 3.0.

5. Xu, R., et al. (2024). IoT-LLM Integration for Equipment Maintenance.

6. Li, M., & Wu, X. (2024). Multilingual LLMs for Global Teams.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and not of the publisher.