@inproceedings{liao-etal-2024-medcare,
title = "{M}ed{C}are: Advancing Medical {LLM}s through Decoupling Clinical Alignment and Knowledge Aggregation",
author = "Liao, Yusheng and
Jiang, Shuyang and
Chen, Zhe and
Wang, Yu and
Wang, Yanfeng",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.619",
pages = "10562--10581",
abstract = "Large language models (LLMs) have shown substantial progress in natural language understanding and generation, proving valuable especially in the medical field. Despite advancements, challenges persist due to the complexity and diversity inherent in medical tasks, which can be categorized as knowledge-intensive tasks and alignment-required tasks. Previous approaches either ignore the latter task or focus on a minority of tasks and hence lose generalization. To address these drawbacks, we propose a progressive fine-tuning pipeline. This pipeline employs a and a to encode diverse knowledge in the first stage and filter out detrimental information. In the second stage, we drop the to avoid the interference of suboptimal representation and leverage an additional alignment module optimized towards an orthogonal direction to the knowledge space to mitigate knowledge forgetting. Based on this two-stage paradigm, we proposed a \textbf{Med}ical LLM through decoupling \textbf{C}linical \textbf{A}lignment and Knowledge Agg\textbf{re}gation (), which is designed to achieve promising performance on over 20 medical tasks, as well as results on specific medical alignment tasks. Various model sizes of (1.8B, 7B, 14B) all demonstrate significant improvements over existing models with similar model sizes. Our code and datasets are available at \url{https://github.com/BlueZeros/MedCare}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liao-etal-2024-medcare">
<titleInfo>
<title>MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yusheng</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuyang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanfeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have shown substantial progress in natural language understanding and generation, proving valuable especially in the medical field. Despite advancements, challenges persist due to the complexity and diversity inherent in medical tasks, which can be categorized as knowledge-intensive tasks and alignment-required tasks. Previous approaches either ignore the latter task or focus on a minority of tasks and hence lose generalization. To address these drawbacks, we propose a progressive fine-tuning pipeline. This pipeline employs a and a to encode diverse knowledge in the first stage and filter out detrimental information. In the second stage, we drop the to avoid the interference of suboptimal representation and leverage an additional alignment module optimized towards an orthogonal direction to the knowledge space to mitigate knowledge forgetting. Based on this two-stage paradigm, we proposed a Medical LLM through decoupling Clinical Alignment and Knowledge Aggregation (), which is designed to achieve promising performance on over 20 medical tasks, as well as results on specific medical alignment tasks. Various model sizes of (1.8B, 7B, 14B) all demonstrate significant improvements over existing models with similar model sizes. Our code and datasets are available at https://github.com/BlueZeros/MedCare.</abstract>
<identifier type="citekey">liao-etal-2024-medcare</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.619</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>10562</start>
<end>10581</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation
%A Liao, Yusheng
%A Jiang, Shuyang
%A Chen, Zhe
%A Wang, Yu
%A Wang, Yanfeng
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F liao-etal-2024-medcare
%X Large language models (LLMs) have shown substantial progress in natural language understanding and generation, proving valuable especially in the medical field. Despite advancements, challenges persist due to the complexity and diversity inherent in medical tasks, which can be categorized as knowledge-intensive tasks and alignment-required tasks. Previous approaches either ignore the latter task or focus on a minority of tasks and hence lose generalization. To address these drawbacks, we propose a progressive fine-tuning pipeline. This pipeline employs a and a to encode diverse knowledge in the first stage and filter out detrimental information. In the second stage, we drop the to avoid the interference of suboptimal representation and leverage an additional alignment module optimized towards an orthogonal direction to the knowledge space to mitigate knowledge forgetting. Based on this two-stage paradigm, we proposed a Medical LLM through decoupling Clinical Alignment and Knowledge Aggregation (), which is designed to achieve promising performance on over 20 medical tasks, as well as results on specific medical alignment tasks. Various model sizes of (1.8B, 7B, 14B) all demonstrate significant improvements over existing models with similar model sizes. Our code and datasets are available at https://github.com/BlueZeros/MedCare.
%U https://aclanthology.org/2024.findings-emnlp.619
%P 10562-10581
Markdown (Informal)
[MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation](https://aclanthology.org/2024.findings-emnlp.619) (Liao et al., Findings 2024)
ACL