부산대학교 도서관

Given the widespread integration of Artificial Intelligence across various domains, the exploration of its applications in the legal field remains understudied, emphasizing the critical need for the development of effective deep learning approaches. This paper describes on our approaches to legal information retrieval (Task 1) and legal question answering (Task 2) in the Automated Legal Question Answering Competition (ALQAC 2023). Specifically, we employed the Paraformer model for information retrieval and leveraged large language models for answering questions. In the competition, we achieved the 1 st place for Task 2. In this task, our findings demonstrate that fine-tuning appropriate prompts helps the large language models to achieve better performance. Our prompts are available at https://github.com/DucLong06/Legal-Prompts