Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.08792 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916246190030848 |
|---|---|
| author | Sepulveda, Edison Jair Bejarano Hector, Nicolai Potes Montoya, Santiago Pineda Rodriguez, Felipe Ivan Orduy, Jaime Enrique Cabezas, Alec Rosales Navarrete, Danny Traslaviña Farfan, Sergio Madrid |
| author_facet | Sepulveda, Edison Jair Bejarano Hector, Nicolai Potes Montoya, Santiago Pineda Rodriguez, Felipe Ivan Orduy, Jaime Enrique Cabezas, Alec Rosales Navarrete, Danny Traslaviña Farfan, Sergio Madrid |
| contents | This paper explores the potential of large language models (LLMs) to make the Aeronautical Regulations of Colombia (RAC) more accessible. Given the complexity and extensive technicality of the RAC, this study introduces a novel approach to simplifying these regulations for broader understanding. By developing the first-ever RAC database, which contains 24,478 expertly labeled question-and-answer pairs, and fine-tuning LLMs specifically for RAC applications, the paper outlines the methodology for dataset assembly, expert-led annotation, and model training. Utilizing the Gemma1.1 2b model along with advanced techniques like Unsloth for efficient VRAM usage and flash attention mechanisms, the research aims to expedite training processes. This initiative establishes a foundation to enhance the comprehensibility and accessibility of RAC, potentially benefiting novices and reducing dependence on expert consultations for navigating the aviation industry's regulatory landscape.
You can visit the dataset (https://huggingface.co/somosnlp/gemma-1.1-2b-it_ColombiaRAC_FullyCurated_format_chatML_V1) and the model (https://huggingface.co/datasets/somosnlp/ColombiaRAC_FullyCurated) here. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_08792 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Enhanced RAC Accessibility: Leveraging Datasets and LLMs Sepulveda, Edison Jair Bejarano Hector, Nicolai Potes Montoya, Santiago Pineda Rodriguez, Felipe Ivan Orduy, Jaime Enrique Cabezas, Alec Rosales Navarrete, Danny Traslaviña Farfan, Sergio Madrid Machine Learning Artificial Intelligence This paper explores the potential of large language models (LLMs) to make the Aeronautical Regulations of Colombia (RAC) more accessible. Given the complexity and extensive technicality of the RAC, this study introduces a novel approach to simplifying these regulations for broader understanding. By developing the first-ever RAC database, which contains 24,478 expertly labeled question-and-answer pairs, and fine-tuning LLMs specifically for RAC applications, the paper outlines the methodology for dataset assembly, expert-led annotation, and model training. Utilizing the Gemma1.1 2b model along with advanced techniques like Unsloth for efficient VRAM usage and flash attention mechanisms, the research aims to expedite training processes. This initiative establishes a foundation to enhance the comprehensibility and accessibility of RAC, potentially benefiting novices and reducing dependence on expert consultations for navigating the aviation industry's regulatory landscape. You can visit the dataset (https://huggingface.co/somosnlp/gemma-1.1-2b-it_ColombiaRAC_FullyCurated_format_chatML_V1) and the model (https://huggingface.co/datasets/somosnlp/ColombiaRAC_FullyCurated) here. |
| title | Towards Enhanced RAC Accessibility: Leveraging Datasets and LLMs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2405.08792 |