<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsunokake-etal-2026-micro">
    <titleInfo>
        <title>Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Masaya</namePart>
        <namePart type="family">Tsunokake</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuta</namePart>
        <namePart type="family">Koreeda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Terufumi</namePart>
        <namePart type="family">Morishita</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Koichi</namePart>
        <namePart type="family">Nagatsuka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hikaru</namePart>
        <namePart type="family">Tomonari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yasuhiro</namePart>
        <namePart type="family">Sogawa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yevgen</namePart>
            <namePart type="family">Matusevych</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gülşen</namePart>
            <namePart type="family">Eryiğit</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolaos</namePart>
            <namePart type="family">Aletras</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-384-5</identifier>
    </relatedItem>
    <abstract>When applying LLMs to real-world enterprise operations, LLMs need to handle proprietary knowledge in small domains of specific operations (micro domains).A previous study shows micro domain-adaptive pre-training (mDAPT) with fewer documents is effective, similarly to DAPT in larger domains.However, it evaluates mDAPT only on multiple-choice questions; thus, its effectiveness for generative tasks in real-world operations remains unknown.We aim to reveal the potential and bottlenecks of mDAPT for generative tasks.To this end, we disentangle the answering process into three subtasks and evaluate the performance of each subtask: (1) eliciting facts relevant to questions from an LLM’s own knowledge, (2) reasoning over the facts to obtain conclusions, and (3) composing long-form answers based on the conclusions.We verified mDAPT on proprietary IT product knowledge for real-world questions in IT technical support operations. As a result, mDAPT resolved the elicitation task that the base model struggled with but did not resolve other subtasks.This clarifies mDAPT’s effectiveness in the knowledge aspect and its bottlenecks in other aspects.Further analysis empirically shows that resolving the elicitation and reasoning tasks ensures sufficient performance (over 90%), emphasizing the need to enhance reasoning capability.</abstract>
    <identifier type="citekey">tsunokake-etal-2026-micro</identifier>
    <location>
        <url>https://aclanthology.org/2026.eacl-industry.22/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>304</start>
            <end>316</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks
%A Tsunokake, Masaya
%A Koreeda, Yuta
%A Morishita, Terufumi
%A Nagatsuka, Koichi
%A Tomonari, Hikaru
%A Sogawa, Yasuhiro
%Y Matusevych, Yevgen
%Y Eryiğit, Gülşen
%Y Aletras, Nikolaos
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-384-5
%F tsunokake-etal-2026-micro
%X When applying LLMs to real-world enterprise operations, LLMs need to handle proprietary knowledge in small domains of specific operations (micro domains).A previous study shows micro domain-adaptive pre-training (mDAPT) with fewer documents is effective, similarly to DAPT in larger domains.However, it evaluates mDAPT only on multiple-choice questions; thus, its effectiveness for generative tasks in real-world operations remains unknown.We aim to reveal the potential and bottlenecks of mDAPT for generative tasks.To this end, we disentangle the answering process into three subtasks and evaluate the performance of each subtask: (1) eliciting facts relevant to questions from an LLM’s own knowledge, (2) reasoning over the facts to obtain conclusions, and (3) composing long-form answers based on the conclusions.We verified mDAPT on proprietary IT product knowledge for real-world questions in IT technical support operations. As a result, mDAPT resolved the elicitation task that the base model struggled with but did not resolve other subtasks.This clarifies mDAPT’s effectiveness in the knowledge aspect and its bottlenecks in other aspects.Further analysis empirically shows that resolving the elicitation and reasoning tasks ensures sufficient performance (over 90%), emphasizing the need to enhance reasoning capability.
%U https://aclanthology.org/2026.eacl-industry.22/
%P 304-316

Markdown (Informal)

[Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks](https://aclanthology.org/2026.eacl-industry.22/) (Tsunokake et al., EACL 2026)

• Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks (Tsunokake et al., EACL 2026)

ACL

• Masaya Tsunokake, Yuta Koreeda, Terufumi Morishita, Koichi Nagatsuka, Hikaru Tomonari, and Yasuhiro Sogawa. 2026. Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track), pages 304–316, Rabat, Morocco. Association for Computational Linguistics.