Paper Title
Automating and Enhancing Requirement Engineering Process Through Large Language Models

Abstract
The requirement engineering activities in automotive, aircraft, software, and manufacturing are all complicated—no kidding—extensive documentation, lots of stakeholders, and must comply with stringent standards. The tools available at present have proved inadequate for handling long, complex texts, thus becoming sources of inefficiencies and errors. The study investigates the application of LLMs in requirements engineering, such as Wizard-Vicuna-13B-Uncensored-GPTQ and Nous-Hermes-13B-GPTQ, for enhancement and partial automation. It suggests a local GGT Q&A retrieval framework combining advanced AI techniques for accurate extraction and validation, addressing specific challenges in the context of specialized language in data privacy. Innovating such mechanisms completes the existing ones for increased efficiency, accuracy, and scalability, leading to better overall applications. Future work will address existing limitations, including wider contexts, and develop the model to further support more diverse engineering processes and business applications. Keywords - Requirement Engineering, Q&A Retrieval Solution, Large Language Models