Lawyer LLaMA

Through instruction fine-tuning, the LLaMA model shows very good performance in general fields. However, due to the lack of suitable data, few people have explored the capabilities of LLaMA in the legal field. To fill this gap, we propose Lawyer LLaMA, a model additionally trained on legal domain data.
Lawyer LLaMA first conducted continual pretraining on a large-scale legal corpus, allowing it to systematically learn the Chinese legal knowledge system. On this basis, we used ChatGPT to collect a batch of analysis of objective questions on China’s National Unified Legal Professional Qualification Examination (hereinafter referred to as the legal exam) and responses to legal consultations. We used the collected data to fine-tune the model and let the model Acquire the ability to apply legal knowledge to specific scenarios.