arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.08792cs.LGcs.AI
收藏

迈向增强的RAC可访问性:利用数据集与大语言模型

Towards Enhanced RAC Accessibility: Leveraging Datasets and LLMs

Universidad de Barcelona(巴塞罗那大学);Universidad Nacional de Colombia(哥伦比亚国立大学);Fund. Univ. Los Libertadores(自由者大学基金会)
Edison Jair Bejarano Sepulveda, Nicolai Potes Hector, Santiago Pineda Montoya, Felipe Ivan Rodriguez, Jaime Enrique Orduy, Alec Rosales Cabezas, Danny Traslaviñ… 展开作者

Edison Jair Bejarano Sepulveda, Nicolai Potes Hector, Santiago Pineda Montoya, Felipe Ivan Rodriguez, Jaime Enrique Orduy, Alec Rosales Cabezas, Danny Traslaviña Navarrete, Sergio Madrid Farfan

AI总结:

为提升哥伦比亚航空条例(RAC)的可访问性,研究构建了含24478条专家标注问答对的首个RAC数据集,结合Unsloth、flash attention等技术微调Gemma1.1 2b模型,为降低RAC理解门槛、减少专家咨询依赖奠定基础。

摘要:

本文探讨了大语言模型(LLM)提升哥伦比亚航空条例(RAC)可访问性的潜力。鉴于RAC的复杂性与极强的专业性,本研究提出了一种简化这些条例以扩大受众理解范围的新方法。通过构建首个RAC数据库(包含24478条经专家标注的问答对),并针对RAC应用场景微调LLM,本文阐述了数据集组装、专家主导标注及模型训练的方法论。研究采用Gemma1.1 2b模型,结合Unsloth(实现高效显存占用)与flash attention机制等先进技术,旨在加快训练进程。该举措为提升RAC的可理解性与可访问性奠定了基础,有望惠及新手,并降低航空业监管领域咨询专家的依赖。你可在此处访问数据集(https://huggingface.co/somosnlp/gemma-1.1-2b-it_ColombiaRAC_FullyCurated_format_chatML_V1)与模型(https://huggingface.co/datasets/somosnlp/ColombiaRAC_FullyCurated)。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑