In this study, we introduced iterative prompting, which allows one to interact with LLMs more effectively and efficiently through multi-turn interaction. Specifically, we proposed a three-turn iterative prompting approach to food effect summarization in which the keyword-focused and length-controlled prompts are respectively provided to refine the quality of generated summaries. We conducted extensive evaluations, ranging from automated metrics to FDA professionals, on 100 NDA review documents (retrieved from Drugs@FDA) selected over the past five years. We observed that the summary quality is progressively improved throughout the iterative prompting process. Importantly, all the FDA professionals unanimously rated that 85% of the summaries generated by GPT-4 are factually consistent with the golden reference summary. Taken together, these results strongly suggest a great potential for LLMs to provide food effect summaries that could be reviewed by FDA professionals, thereby improving the efficiency of the PSG assessment cycle and promoting generic drug product development.
Learning Objectives:
1. To acknowledge the potential of LLMs in supporting generic drug product development and regulatory assessment.
2. To identify the advantages of using iterative prompting approach when interacting with LLMs.
