Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Christophe, Clément, Raha, Tathagata, Maslenkova, Svetlana, Salman, Muhammad Umar, Kanithi, Praveen K, Pimentel, Marco AF, Khan, Shadab
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910617488588800
author Christophe, Clément
Raha, Tathagata
Maslenkova, Svetlana
Salman, Muhammad Umar
Kanithi, Praveen K
Pimentel, Marco AF
Khan, Shadab
author_facet Christophe, Clément
Raha, Tathagata
Maslenkova, Svetlana
Salman, Muhammad Umar
Kanithi, Praveen K
Pimentel, Marco AF
Khan, Shadab
contents Large Language Models (LLMs) have demonstrated significant potential in transforming clinical applications. In this study, we investigate the efficacy of four techniques in adapting LLMs for clinical use-cases: continuous pretraining, instruct fine-tuning, NEFTune, and prompt engineering. We employ these methods on Mistral 7B and Mixtral 8x7B models, leveraging a large-scale clinical pretraining dataset of 50 billion tokens and an instruct fine-tuning dataset of 500 million tokens. Our evaluation across various clinical tasks reveals the impact of each technique. While continuous pretraining beyond 250 billion tokens yields marginal improvements on its own, it establishes a strong foundation for instruct fine-tuning. Notably, NEFTune, designed primarily to enhance generation quality, surprisingly demonstrates additional gains on our benchmark. Complex prompt engineering methods further enhance performance. These findings show the importance of tailoring fine-tuning strategies and exploring innovative techniques to optimize LLM performance in the clinical domain.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14988
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs
Christophe, Clément
Raha, Tathagata
Maslenkova, Svetlana
Salman, Muhammad Umar
Kanithi, Praveen K
Pimentel, Marco AF
Khan, Shadab
Computation and Language
Large Language Models (LLMs) have demonstrated significant potential in transforming clinical applications. In this study, we investigate the efficacy of four techniques in adapting LLMs for clinical use-cases: continuous pretraining, instruct fine-tuning, NEFTune, and prompt engineering. We employ these methods on Mistral 7B and Mixtral 8x7B models, leveraging a large-scale clinical pretraining dataset of 50 billion tokens and an instruct fine-tuning dataset of 500 million tokens. Our evaluation across various clinical tasks reveals the impact of each technique. While continuous pretraining beyond 250 billion tokens yields marginal improvements on its own, it establishes a strong foundation for instruct fine-tuning. Notably, NEFTune, designed primarily to enhance generation quality, surprisingly demonstrates additional gains on our benchmark. Complex prompt engineering methods further enhance performance. These findings show the importance of tailoring fine-tuning strategies and exploring innovative techniques to optimize LLM performance in the clinical domain.
title Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs
topic Computation and Language
url https://arxiv.org/abs/2409.14988