@inproceedings{jiang-etal-2024-improving,
title = "Improving Referring Ability for Biomedical Language Models",
author = "Jiang, Junfeng and
Cheng, Fei and
Aizawa, Akiko",
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.375/",
doi = "10.18653/v1/2024.findings-emnlp.375",
pages = "6444--6457",
abstract = "Existing auto-regressive large language models (LLMs) are primarily trained using documents from general domains. In the biomedical domain, continual pre-training is a prevalent method for domain adaptation to inject professional knowledge into powerful LLMs that have been pre-trained in general domains. Previous studies typically conduct standard pre-training by randomly packing multiple documents into a long pre-training sequence. Recently, some existing works suggest that enhancing the relatedness of documents within the same pre-training sequence may be advantageous. However, these studies primarily focus on general domains, which cannot be readily applied in the biomedical domain where the distinction of fine-grained topics is harder. Is it possible to further improve the pre-training for biomedical language models (LMs) using exactly the same corpus? In this paper, we explore an improved approach to continual pre-training, which is a prevalent method for domain adaptation, by utilizing information from the citation network in this challenging scenario. Empirical studies demonstrate that our proposed LinkLM data improves both the intra-sample and inter-sample referring abilities of auto-regressive LMs in the biomedical domain, encouraging more profound consideration of task-specific pre-training sequence design for continual pre-training."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2024-improving">
<titleInfo>
<title>Improving Referring Ability for Biomedical Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junfeng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Aizawa</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>Existing auto-regressive large language models (LLMs) are primarily trained using documents from general domains. In the biomedical domain, continual pre-training is a prevalent method for domain adaptation to inject professional knowledge into powerful LLMs that have been pre-trained in general domains. Previous studies typically conduct standard pre-training by randomly packing multiple documents into a long pre-training sequence. Recently, some existing works suggest that enhancing the relatedness of documents within the same pre-training sequence may be advantageous. However, these studies primarily focus on general domains, which cannot be readily applied in the biomedical domain where the distinction of fine-grained topics is harder. Is it possible to further improve the pre-training for biomedical language models (LMs) using exactly the same corpus? In this paper, we explore an improved approach to continual pre-training, which is a prevalent method for domain adaptation, by utilizing information from the citation network in this challenging scenario. Empirical studies demonstrate that our proposed LinkLM data improves both the intra-sample and inter-sample referring abilities of auto-regressive LMs in the biomedical domain, encouraging more profound consideration of task-specific pre-training sequence design for continual pre-training.</abstract>
<identifier type="citekey">jiang-etal-2024-improving</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.375</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.375/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>6444</start>
<end>6457</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Referring Ability for Biomedical Language Models
%A Jiang, Junfeng
%A Cheng, Fei
%A Aizawa, Akiko
%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 jiang-etal-2024-improving
%X Existing auto-regressive large language models (LLMs) are primarily trained using documents from general domains. In the biomedical domain, continual pre-training is a prevalent method for domain adaptation to inject professional knowledge into powerful LLMs that have been pre-trained in general domains. Previous studies typically conduct standard pre-training by randomly packing multiple documents into a long pre-training sequence. Recently, some existing works suggest that enhancing the relatedness of documents within the same pre-training sequence may be advantageous. However, these studies primarily focus on general domains, which cannot be readily applied in the biomedical domain where the distinction of fine-grained topics is harder. Is it possible to further improve the pre-training for biomedical language models (LMs) using exactly the same corpus? In this paper, we explore an improved approach to continual pre-training, which is a prevalent method for domain adaptation, by utilizing information from the citation network in this challenging scenario. Empirical studies demonstrate that our proposed LinkLM data improves both the intra-sample and inter-sample referring abilities of auto-regressive LMs in the biomedical domain, encouraging more profound consideration of task-specific pre-training sequence design for continual pre-training.
%R 10.18653/v1/2024.findings-emnlp.375
%U https://aclanthology.org/2024.findings-emnlp.375/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.375
%P 6444-6457
Markdown (Informal)
[Improving Referring Ability for Biomedical Language Models](https://aclanthology.org/2024.findings-emnlp.375/) (Jiang et al., Findings 2024)
ACL