Generative Models for Domain-Specific Summarization

Abstract

This project evaluates the performance of generative models of summarization in aviation safety domain. Models such as DaVinci, Text-DaVinci-003, and GPT-3.5-Turbo were analyzed in both their zero-shot learning and fine-tuned performance against state-of-the-art models. In zero-shot learning, generative models were superior in most cases to the state-of-the- art models, whereas the fine-tuned models could learn with less information about the dataset. These results predict promising advances in the summarization space to address current limitations in the field.