# Should LLMs be over empowered for high-stake regulatory research?

## TL;DR

This paper examines the use of open-source large language models in regulatory research, highlighting both their potential and limitations.

## Contribution

The paper introduces intuitive strategies to mitigate challenges in using LLMs for high-stake regulatory tasks.

## Key findings

- Flan-T5 models can extract pharmacokinetic interactions and intrinsic factors from drug labels with high precision.
- Challenges include computational constraints, performance variability, and prompt sensitivity.
- Misclassification risks remain a concern for high-stake regulatory applications.

## Abstract

This letter critically evaluates the feasibility of implementing open-source large language models in regulatory research, building upon the recent study on zero-shot and few-shot learning approaches for regulatory tasks. While the study demonstrates that models like Flan-T5 can effectively extract pharmacokinetic drug–drug interactions and intrinsic factors from Food and Drug Administration (US) drug labels with high precision, it also highlights significant challenges, including computational constraints, performance variability, prompt sensitivity, and the risk of misclassification. To address these issues, this letter discusses intuitive ways for mitigating these limitations.