<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ravikumar-batista-navarro-2026-tasks">
    <titleInfo>
        <title>When Tasks Share Structure: A Comparative Study of Training Strategies for Generative Event Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rishi</namePart>
        <namePart type="family">Ravikumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Riza</namePart>
        <namePart type="family">Batista-Navarro</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ali</namePart>
            <namePart type="family">Hürriyetoğlu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Surendrabikram</namePart>
            <namePart type="family">Thapa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hristo</namePart>
            <namePart type="family">Tanev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-402-6</identifier>
    </relatedItem>
    <abstract>Event extraction requires performing two interdependent subtasks: event detection and event argument extraction. While prior work has explored pipelined and joint training approaches, the question of how best to coordinate training across these subtasks in generative LLM-based systems remains open. We present a systematic study comparing three training paradigms: disjoint, fully shared and hybrid weight allocation, instantiated as eight concrete strategies and evaluated on ACE2005 and RichERE across multiple instruction-tuned LLMs. Our findings show that training strategy has a consistent and meaningful effect on extraction accuracy, and that a clear best-performing strategy emerges across models and benchmarks. We believe that these findings could extend beyond event extraction to other information extraction tasks that decompose into interdependent subtasks.</abstract>
    <identifier type="citekey">ravikumar-batista-navarro-2026-tasks</identifier>
    <location>
        <url>https://aclanthology.org/2026.eeuca-1.5/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>38</start>
            <end>48</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When Tasks Share Structure: A Comparative Study of Training Strategies for Generative Event Extraction
%A Ravikumar, Rishi
%A Batista-Navarro, Riza
%Y Hürriyetoğlu, Ali
%Y Thapa, Surendrabikram
%Y Tanev, Hristo
%S Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-402-6
%F ravikumar-batista-navarro-2026-tasks
%X Event extraction requires performing two interdependent subtasks: event detection and event argument extraction. While prior work has explored pipelined and joint training approaches, the question of how best to coordinate training across these subtasks in generative LLM-based systems remains open. We present a systematic study comparing three training paradigms: disjoint, fully shared and hybrid weight allocation, instantiated as eight concrete strategies and evaluated on ACE2005 and RichERE across multiple instruction-tuned LLMs. Our findings show that training strategy has a consistent and meaningful effect on extraction accuracy, and that a clear best-performing strategy emerges across models and benchmarks. We believe that these findings could extend beyond event extraction to other information extraction tasks that decompose into interdependent subtasks.
%U https://aclanthology.org/2026.eeuca-1.5/
%P 38-48

Markdown (Informal)

[When Tasks Share Structure: A Comparative Study of Training Strategies for Generative Event Extraction](https://aclanthology.org/2026.eeuca-1.5/) (Ravikumar & Batista-Navarro, EEUCA 2026)

• When Tasks Share Structure: A Comparative Study of Training Strategies for Generative Event Extraction (Ravikumar & Batista-Navarro, EEUCA 2026)

ACL

• Rishi Ravikumar and Riza Batista-Navarro. 2026. When Tasks Share Structure: A Comparative Study of Training Strategies for Generative Event Extraction. In Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026), pages 38–48, San Diego, California, USA. Association for Computational Linguistics.