<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yano-miwa-2025-effect">
    <titleInfo>
        <title>Effect of Multilingual and Domain-adapted Continual Pre-training on Few-shot Promptability</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ken</namePart>
        <namePart type="family">Yano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Makoto</namePart>
        <namePart type="family">Miwa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 24th Workshop on Biomedical Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dina</namePart>
            <namePart type="family">Demner-Fushman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sophia</namePart>
            <namePart type="family">Ananiadou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Makoto</namePart>
            <namePart type="family">Miwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Junichi</namePart>
            <namePart type="family">Tsujii</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Viena, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-275-6</identifier>
    </relatedItem>
    <abstract>Continual Pre-training (CPT) can help pre-trained large language models (LLMs) effectively adapt to new or under-trained domains or low-resource languages without re-training from scratch.Nevertheless, during CPT, the model’s few-shot transfer ability is known to be affected for emergent tasks.We verified this by comparing the performance between the few-shot and fine-tuning settings on the same tasks.We used Llama3-ELAINE-medLLM, which was continually pre-trained on Llama3-8B, targeted for the biomedical domain, and adapted for multilingual languages (English, Japanese, and Chinese).We compared the performance of Llama3-ELAINE-medLLM and Llama3-8B in three emergent tasks: two related domain tasks, entity recognition (NER) and machine translation (MT), and one out-of-domain task, summarization (SUM). Our experimental results show that degradation in few-shot transfer ability does not necessarily indicate the model’s underlying potential on the same task after fine-tuning.</abstract>
    <identifier type="citekey">yano-miwa-2025-effect</identifier>
    <identifier type="doi">10.18653/v1/2025.bionlp-1.2</identifier>
    <location>
        <url>https://aclanthology.org/2025.bionlp-1.2/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>18</start>
            <end>26</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Effect of Multilingual and Domain-adapted Continual Pre-training on Few-shot Promptability
%A Yano, Ken
%A Miwa, Makoto
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Tsujii, Junichi
%S Proceedings of the 24th Workshop on Biomedical Language Processing
%D 2025
%8 August
%I Association for Computational Linguistics
%C Viena, Austria
%@ 979-8-89176-275-6
%F yano-miwa-2025-effect
%X Continual Pre-training (CPT) can help pre-trained large language models (LLMs) effectively adapt to new or under-trained domains or low-resource languages without re-training from scratch.Nevertheless, during CPT, the model’s few-shot transfer ability is known to be affected for emergent tasks.We verified this by comparing the performance between the few-shot and fine-tuning settings on the same tasks.We used Llama3-ELAINE-medLLM, which was continually pre-trained on Llama3-8B, targeted for the biomedical domain, and adapted for multilingual languages (English, Japanese, and Chinese).We compared the performance of Llama3-ELAINE-medLLM and Llama3-8B in three emergent tasks: two related domain tasks, entity recognition (NER) and machine translation (MT), and one out-of-domain task, summarization (SUM). Our experimental results show that degradation in few-shot transfer ability does not necessarily indicate the model’s underlying potential on the same task after fine-tuning.
%R 10.18653/v1/2025.bionlp-1.2
%U https://aclanthology.org/2025.bionlp-1.2/
%U https://doi.org/10.18653/v1/2025.bionlp-1.2
%P 18-26

Markdown (Informal)

[Effect of Multilingual and Domain-adapted Continual Pre-training on Few-shot Promptability](https://aclanthology.org/2025.bionlp-1.2/) (Yano & Miwa, BioNLP 2025)

• Effect of Multilingual and Domain-adapted Continual Pre-training on Few-shot Promptability (Yano & Miwa, BioNLP 2025)

ACL

• Ken Yano and Makoto Miwa. 2025. Effect of Multilingual and Domain-adapted Continual Pre-training on Few-shot Promptability. In Proceedings of the 24th Workshop on Biomedical Language Processing, pages 18–26, Viena, Austria. Association for Computational Linguistics.