Large Language Models as Instructors: A Study on Multilingual Clinical Entity Extraction - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Large Language Models as Instructors: A Study on Multilingual Clinical Entity Extraction

Abstract

In clinical and other specialized domains, data are scarce due to their confidential nature. This lack of data is a major problem when finetuning language models. Nevertheless, very large language models (LLMs) are promising for the medical domain but cannot be used directly in healthcare facilities due to data confidentiality issues. We explore an approach of annotating training data with LLMs to train smaller models more adapted to our problem. We show that this method yields promising results for information extraction tasks.
Fichier principal
Vignette du fichier
2023.bionlp-1.15.pdf (840.38 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Licence : CC BY - Attribution

Dates and versions

hal-04394012 , version 1 (15-01-2024)

Identifiers

Cite

Simon Meoni, Theo Ryffel, Eric Villemonte de La Clergerie. Large Language Models as Instructors: A Study on Multilingual Clinical Entity Extraction. The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, Jul 2023, Toronto, Canada. pp.178-190, ⟨10.18653/v1/2023.bionlp-1.15⟩. ⟨hal-04394012⟩

Collections

INRIA INRIA2
21 View
29 Download

Altmetric

Share

Gmail Facebook X LinkedIn More