Automation, Control and Intelligent Systems

Submit a Manuscript

Publishing with us to make your research visible to the widest possible audience.

Propose a Special Issue

Building a community of authors and readers to discuss the latest research and develop new ideas.

Prospects and Challenges of Large Language Models in the Field of Intelligent Building

At the end of November 2022, the ChatGPT released by OpenAI Inc. performed excellently and quickly became popular worldwide. Despite some shortcomings, Large Language Models (LLM) represented by Generative Pre-trained Transformer (GPT) is here to stay, leading the way for the new generation of Natural Language Processing (NLP) technique. This commentary presents the potential benefits and challenges of the applications of large language models, from the viewpoint of intelligent building. We briefly discuss the history and current state of large language models and their shortcomings. We then highlight how these models can be used to improve the daily maintenance of intelligent building. With regard to challenges, we address some vital problems to be solved before deployment and argue that large language models in intelligent building require maintenance staff to develop sets of competencies and literacies necessary to both understand the technology as well as the maintenance and maneuver of intelligent building. In addition, a clear strategy within intelligent building troops with a strong focus on AI talents construction and training dataset annotation are required to integrate and take full advantage of large language models in the daily maintenance. We conclude with recommendations for how to address these challenges and prepare for further applications of LLM in the field of intelligent building in the future.

Artificial Intelligence, Large Language Models, Intelligent Building

APA Style

Wu Yang, Wang Junjie, Li Weihua. (2023). Prospects and Challenges of Large Language Models in the Field of Intelligent Building. Automation, Control and Intelligent Systems, 11(1), 15-20.

ACS Style

Wu Yang; Wang Junjie; Li Weihua. Prospects and Challenges of Large Language Models in the Field of Intelligent Building. Autom. Control Intell. Syst. 2023, 11(1), 15-20. doi: 10.11648/j.acis.20231101.13

AMA Style

Wu Yang, Wang Junjie, Li Weihua. Prospects and Challenges of Large Language Models in the Field of Intelligent Building. Autom Control Intell Syst. 2023;11(1):15-20. doi: 10.11648/j.acis.20231101.13

Copyright © 2023 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License ( which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

1. Z. Feng, D. Zhang, and G. Rao, “From Turing test to ChatGPT: a milestone of man-machine interaction and its enlightenment,” Chinese Journal of Language Policy and Planning, vol. 8, 2023, pp. 20-24.
2. H. Lu, “ChatGPT Brings Huge Challenges to Traditional Search Engines,” China Economic Times, 2023-02-14, pp. 1.
3. Q. Yang, Y. Zhao, “Domestic and foreign manufacturers accelerate their efforts to compete with AIGC,” The 21st Century Business Herald, 2023-02-08, pp. 11.
4. T. Brown, B. Mann, and N. Ryder, “Language models are few-shot learners,” Advances in neural information processing systems, vol. 33, 2020, pp. 1877-1901.
5. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proceedings of the National Academy of Sciences of the United States of America, vol. 8, 1982, pp. 79.
6. W. Che, T. Liu, “New Paradigm of Natural Language Processing: A Method Based on Pre-Trained Models,” ZTE Technology Journal, vol. 28, 2022, pp. 3–9.
7. A. Radford, K. Narasimhan, and T. Salimans, “Improving language understanding by generative pre-training,” OpenAI blog, 2018.
8. A. Vaswani, N. Shazeer, and N. Parmar. “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017, pp. 48.
9. J. Wei, X. Wang, and D. Schuurmans, “Chain of thought prompting elicits reasoning in large language models,” arXiv preprint, 2022, arXiv: 2201.11903.
10. L. Ouyang, J. Wu, and X. Jiang “Training language models to follow instructions with human feedback,” arXiv preprint, 2022, arXiv: 2203.02155.
11. P. Jie, “Large language model for molecular chemistry,” Nature Computational Science, vol. 1, 2023, pp. 3.
12. X. Qiu, T. Sun, and Y. Xu, “Pre-trained models for natural language processing: A survey,” Science China (Technological Sciences), vol. 10, 2020, pp. 63.
13. S. Kalyan, A. Rajasekharan, S. Sangeetha, “Ammus: A survey of transformer-based pretrained models in natural language processing,” arXiv preprint, 2021, arXiv: 2108.05542.
14. T. Schick, J. Dwivedi-Yu, and R. Dessì, “Toolformer: Language models can teach themselves to use tools,” arXiv preprint, 2023, arXiv: 2302.04761.
15. A. Tamkin, M. Brundage, and J. Clark, “Understanding the capabilities, limitations, and societal impact of large language models,” arXiv preprint, 2021, arXiv: 2102.02503.
16. S. Zheng, “Measured ChatGPT-4: Improved mathematical skills, poor temporal reasoning, difficult to understand the ‘Daiyu inverted pull willow’ network stem”, Sohu blog, 2023,
17. H. Zhang, L. Li, Chun. Li, “ChatGPT Performance Evaluation on Chinese Language and Risk Measures,” Data Analysis and Knowledge Discovery, vol. 3, 2023, pp. 1-14.
18. A. Abubakar, F. Maheen, Z. James, “Large language models associate Muslims with violence,” Nature Machine Intelligence, vol. 6, 2021, pp. 3.
19. S. Wu, X. Wang, R. Xiao, “Problem and Perspective for Battery Researcher Based on Large Language Model,” Energy Storage Science and Technology, vol. 3, 2023, pp. 1-7.