Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain

Aryo Pradipta Gema, Pasquale Minervini, Luke Daines, Tom Hope, Beatrice Alex

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Adapting pretrained language models to novel domains, such as clinical applications, traditionally involves retraining their entire set of parameters. Parameter-Efficient Fine-Tuning (PEFT) techniques for fine-tuning language models significantly reduce computational requirements by selectively fine-tuning small subsets of parameters. In this study, we propose a two-step PEFT framework and evaluate it in the clinical domain. Our approach combines a specialised PEFT adapter layer designed for clinical domain adaptation with another adapter specialised for downstream tasks. We evaluate the framework on multiple clinical outcome prediction datasets, comparing it to clinically trained language models. Our framework achieves a better AUROC score averaged across all clinical downstream tasks compared to clinical language models. In particular, we observe large improvements of 4-5% AUROC in large-scale multilabel classification tasks, such as diagnoses and procedures classification. To our knowledge, this study is the first to provide an extensive empirical analysis of the interplay between PEFT techniques and domain adaptation in an important real-world domain of clinical applications.

Original languageEnglish
Title of host publicationClinicalNLP 2024 - 6th Workshop on Clinical Natural Language Processing, Proceedings of the Workshop
EditorsTristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Danielle Bitterman
PublisherAssociation for Computational Linguistics (ACL)
Pages91-104
Number of pages14
ISBN (Electronic)9798891761094
StatePublished - 2024
Event6th Workshop on Clinical Natural Language Processing, ClinicalNLP 2024, held at NAACL 2024 - Mexico City, Mexico
Duration: 21 Jun 2024 → …

Publication series

NameClinicalNLP 2024 - 6th Workshop on Clinical Natural Language Processing, Proceedings of the Workshop

Conference

Conference6th Workshop on Clinical Natural Language Processing, ClinicalNLP 2024, held at NAACL 2024
Country/TerritoryMexico
CityMexico City
Period21/06/24 → …

Bibliographical note

Publisher Copyright:
© 2024 Association for Computational Linguistics.

Fingerprint

Dive into the research topics of 'Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain'. Together they form a unique fingerprint.

Cite this