Advanced Generative AI Methods for Academic Text Summarization

The exponential growth of scientific literature emphasizes the need for employing advanced techniques for effective text summarization, which can significantly speed up the research process. This study tackles the challenge by advancing scientific text summarization through AI and deep learning methods. We delve into the integration and fine-tuning of cutting-edge models, including LED_Large, Pegasus variants, and BART, aiming to refine the summarization process. Unique combinations, such as SciBERT with LED_Large, were investigated to ensure the capture of critical details frequently missed by traditional methods. This novel approach led to notable improvements in summarization effectiveness. Our findings indicate that models like LED_Large excel in quickly adapting to training data, achieving impressive semantic understanding with fewer training epochs, evidenced by achieving a FRES score of 28.5852 and ROUGE scores, including a ROUGE-l F1-Score of 0.4991. However, while extensively trained models like BART _large and Pegasus displayed strong semantic capabilities, they also pointed to the necessity for refinements in readability and higher-order n-gram overlap in the produced summaries.