Towards Enhanced RAC Accessibility: Leveraging Datasets and LLMs

TL;DR

This study develops a comprehensive RAC question-answer dataset and fine-tunes LLMs to improve accessibility and understanding of Colombian aeronautical regulations, making technical legal content more approachable.

Contribution

Introduces the first RAC dataset with 24,478 labeled QA pairs and fine-tunes LLMs for regulatory applications, enhancing accessibility of complex aeronautical regulations.

Findings

Created a large, expert-labeled RAC QA dataset

Fine-tuned LLMs to interpret and simplify RAC content

Demonstrated improved accessibility for non-experts

Abstract

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.