Developing Prompts to Facilitate Generative Pre-Trained Transformer Classifying Decision-Errors in Flight Operations

Wen-Chin Li; Declan Saunders; Hamed Amanzadeh

doi:10.65351/hsi24.011

Abstract

The emergence of artificial intelligence (AI) with advanced natural language processing offers promising approaches for enhancing the capacity of textual classification. The aviation industry is increasingly interested in adopting AI to improve efficiency, safety, and cost efficiency. This study explores the potential and challenges of using AI to analyse decision errors in flight operations based on the HFACS framework. In pre-training, the model is trained based on a large amount of data to predict the next word in a sequence which allows the model to learn relationships between the words and their meaning in the accident investigation reports. Initial discoveries demonstrated that the AI model could supply a consistent HFACS framework and populate these dimensions with moderate accuracy. Future research is focused on the development of this HFACS-GPT model through fine-tuning and deep learning, facilitating more reliable and consistent conversations.

View the INCOSE record

Download the paper

Citation

BibTeX citation:

@inproceedings{li2024,
  author = {Li, Wen-Chin and Saunders, Declan and Amanzadeh, Hamed},
  editor = {Masson, Dimitri},
  publisher = {INCOSE},
  title = {Developing {Prompts} to {Facilitate} {Generative}
    {Pre-Trained} {Transformer} {Classifying} {Decision-Errors} in
    {Flight} {Operations}},
  booktitle = {Proceedings International Conference on Human Systems
    Integration},
  volume = {3},
  date = {2024-08-29},
  url = {https://hsi-wg.github.io/conferences/HSI2024/proceedings/developing-prompts-to-facilitate-generative-pre-trained-transformer-classifying-decision-errors-in-flight-operations.html},
  doi = {10.65351/hsi24.011},
  langid = {en},
  abstract = {The emergence of artificial intelligence (AI) with
    advanced natural language processing offers promising approaches for
    enhancing the capacity of textual classification. The aviation
    industry is increasingly interested in adopting AI to improve
    efficiency, safety, and cost efficiency. This study explores the
    potential and challenges of using AI to analyse decision errors in
    flight operations based on the HFACS framework. In pre-training, the
    model is trained based on a large amount of data to predict the next
    word in a sequence which allows the model to learn relationships
    between the words and their meaning in the accident investigation
    reports. Initial discoveries demonstrated that the AI model could
    supply a consistent HFACS framework and populate these dimensions
    with moderate accuracy. Future research is focused on the
    development of this HFACS-GPT model through fine-tuning and deep
    learning, facilitating more reliable and consistent conversations.}
}

For attribution, please cite this work as:

Li, Wen-Chin, Declan Saunders, and Hamed Amanzadeh. 2024. “Developing Prompts to Facilitate Generative Pre-Trained Transformer Classifying Decision-Errors in Flight Operations.” In Proceedings International Conference on Human Systems Integration, edited by Dimitri Masson. Vol. 3. INCOSE. https://doi.org/10.65351/hsi24.011.