Opportunities and Pitfalls with Large Language Models for Biomedical Annotation.

Pac Symp Biocomput

Department of Computer and Information Sciences, University of Delaware, Ammon-Pinizzotto Biopharmaceutical Innovation Building, 590 Avenue 1743, Newark, DE19713, US.

Published: December 2024

AI Article Synopsis

  • Large language models (LLMs) depend on high-quality biomedical annotations for training, which are usually created through costly and slow human efforts.
  • LLMs can streamline the curation process, creating a feedback loop where improvements in one area aid the other.
  • The workshop will explore both the benefits and challenges of using LLMs in biomedical annotation and curation, highlighting the current landscape and implications for the future.

Article Abstract

Large language models (LLMs) and biomedical annotations have a symbiotic relationship. LLMs rely on high-quality annotations for training and/or fine-tuning for specific biomedical tasks. These annotations are traditionally generated through expensive and time-consuming human curation. Meanwhile LLMs can also be used to accelerate the process of curation, thus simplifying the process, and potentially creating a virtuous feedback loop. However, their use also introduces new limitations and risks, which are as important to consider as the opportunities they offer. In this workshop, we will review the process that has led to the current rise of LLMs in several fields, and in particular in biomedicine, and discuss specifically the opportunities and pitfalls when they are applied to biomedical annotation and curation.

Download full-text PDF

Source

Publication Analysis

Top Keywords

opportunities pitfalls
8
large language
8
language models
8
biomedical annotation
8
pitfalls large
4
biomedical
4
models biomedical
4
annotation large
4
llms
4
models llms
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!