<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kodama-oda-2026-comprehensive">
    <titleInfo>
        <title>Comprehensive Study of Bilingual and Multi-category Instruction Pre-training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Takashi</namePart>
        <namePart type="family">Kodama</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yusuke</namePart>
        <namePart type="family">Oda</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>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</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">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>Instruction pre-training (IPT) has recently emerged as an effective intermediate stage between vanilla pre-training and post-training for large language models (LLMs). However, the optimal design of IPT corpora—such as the balance between raw and instruction-response data, languages, and task categories—remains unclear. We systematically study IPT corpus composition using a bilingual (English and Japanese) and multi-category (coding, general, math, and reasoning) instruction-response dataset. Through extensive IPT experiments across four base models, including both English-centric and bilingual LLMs, we find that: (1) more instruction-response data generally enhances model performance, particularly for models with large VPT budgets; (2) Japanese instruction data can improve English performance through cross-lingual transfer; and (3) the effectiveness of post-training varies across categories: coding performance is largely determined during IPT, while math and reasoning continue to improve during post-training.</abstract>
    <identifier type="citekey">kodama-oda-2026-comprehensive</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.68/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>1323</start>
            <end>1340</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Comprehensive Study of Bilingual and Multi-category Instruction Pre-training
%A Kodama, Takashi
%A Oda, Yusuke
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F kodama-oda-2026-comprehensive
%X Instruction pre-training (IPT) has recently emerged as an effective intermediate stage between vanilla pre-training and post-training for large language models (LLMs). However, the optimal design of IPT corpora—such as the balance between raw and instruction-response data, languages, and task categories—remains unclear. We systematically study IPT corpus composition using a bilingual (English and Japanese) and multi-category (coding, general, math, and reasoning) instruction-response dataset. Through extensive IPT experiments across four base models, including both English-centric and bilingual LLMs, we find that: (1) more instruction-response data generally enhances model performance, particularly for models with large VPT budgets; (2) Japanese instruction data can improve English performance through cross-lingual transfer; and (3) the effectiveness of post-training varies across categories: coding performance is largely determined during IPT, while math and reasoning continue to improve during post-training.
%U https://aclanthology.org/2026.findings-eacl.68/
%P 1323-1340

Markdown (Informal)

[Comprehensive Study of Bilingual and Multi-category Instruction Pre-training](https://aclanthology.org/2026.findings-eacl.68/) (Kodama & Oda, Findings 2026)

• Comprehensive Study of Bilingual and Multi-category Instruction Pre-training (Kodama & Oda, Findings 2026)

ACL

• Takashi Kodama and Yusuke Oda. 2026. Comprehensive Study of Bilingual and Multi-category Instruction Pre-training. In Findings of the Association for Computational Linguistics: EACL 2026, pages 1323–1340, Rabat, Morocco. Association for Computational Linguistics.