IMPLEMENTATION OF LARGE LANGUAGE MODELS FOR SOFTWARE ENGINEERING SURVERY AND OPEN PROBLEMS

This study explores the implementation of Large Language Models (LLMs) for analyzing open-ended survey responses in software engineering. Traditional surveys often focus on structured, multiple-choice questions, which provide quantitative insights but overlook the depth of qualitative developer feedback. To address this limitation, the project designed and implemented an LLM-powered system capable of summarizing responses, detecting sentiments, identifying recurring themes, and revealing open research problems from unstructured text. The system architecture was built using a three-tier design comprising a frontend interface, backend server, and LLM integration layer. A pre-trained model such as GPT was connected via API to process textual data. The study followed a design and implementation-oriented methodology, including data collection from developer surveys, system development, testing, and evaluation. Performance was assessed using both quantitative and qualitative metrics such as accuracy, coherence, and user feedback. Evaluation results demonstrated that the system effectively automated key qualitative analysis tasks with high accuracy and interpretability. However, challenges such as occasional hallucinations, dependency on third-party APIs, and limited dataset scope were noted. Overall, the findings confirm that LLMs can significantly enhance qualitative research in software engineering by providing faster, more consistent, and context-aware insights. The study concludes that integrating LLMs with human oversight presents a promising approach for future software engineering research anddecision-making