<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-2026-gladiators">
    <titleInfo>
        <title>Gladiators at #SMM4H–HeaRD 2026: Multi-Seed XLM-RoBERTa Ensemble with Focal Loss and Per-Language Threshold Optimization for Multilingual Adverse Drug Event Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ankit</namePart>
        <namePart type="given">Kumar</namePart>
        <namePart type="family">Singh</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 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Guillermo</namePart>
            <namePart type="family">Lopez-Garcia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Graciela</namePart>
            <namePart type="family">Gonzalez-Hernandez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-432-3</identifier>
    </relatedItem>
    <abstract>This paper describes the Gladiators system for Task 1 of the SMM4H 2026 shared task on binary classification of adverse drug event (ADE) mentions in multilingual social media posts. Our system fine-tunes three XLM-RoBERTa large models with different random seeds using focal loss (\ensuremathα=0.75, \ensuremathγ=2.0) and 3× positive oversampling, then averages their predicted probabilities and applies per-language threshold optimization. On the development set, our ensemble achieves a pooled binary F1 of 0.7505. On the official test set—which introduced surprise Farsi comprising 35.5% of samples—our system achieves F1 = 0.6039, above the competition mean (0.5465) and median (0.5798). We evaluated eleven approaches and document key negative results. Post evaluation, a six-model cross-regime ensembleimproved dev F1 to 0.7585.</abstract>
    <identifier type="citekey">singh-2026-gladiators</identifier>
    <location>
        <url>https://aclanthology.org/2026.smm4h-1.2/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>7</start>
            <end>11</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Gladiators at #SMM4H–HeaRD 2026: Multi-Seed XLM-RoBERTa Ensemble with Focal Loss and Per-Language Threshold Optimization for Multilingual Adverse Drug Event Detection
%A Singh, Ankit Kumar
%Y Lopez-Garcia, Guillermo
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, United States
%@ 979-8-89176-432-3
%F singh-2026-gladiators
%X This paper describes the Gladiators system for Task 1 of the SMM4H 2026 shared task on binary classification of adverse drug event (ADE) mentions in multilingual social media posts. Our system fine-tunes three XLM-RoBERTa large models with different random seeds using focal loss (\ensuremathα=0.75, \ensuremathγ=2.0) and 3× positive oversampling, then averages their predicted probabilities and applies per-language threshold optimization. On the development set, our ensemble achieves a pooled binary F1 of 0.7505. On the official test set—which introduced surprise Farsi comprising 35.5% of samples—our system achieves F1 = 0.6039, above the competition mean (0.5465) and median (0.5798). We evaluated eleven approaches and document key negative results. Post evaluation, a six-model cross-regime ensembleimproved dev F1 to 0.7585.
%U https://aclanthology.org/2026.smm4h-1.2/
%P 7-11

Markdown (Informal)

[Gladiators at #SMM4H–HeaRD 2026: Multi-Seed XLM-RoBERTa Ensemble with Focal Loss and Per-Language Threshold Optimization for Multilingual Adverse Drug Event Detection](https://aclanthology.org/2026.smm4h-1.2/) (Singh, SMM4H 2026)

• Gladiators at #SMM4H–HeaRD 2026: Multi-Seed XLM-RoBERTa Ensemble with Focal Loss and Per-Language Threshold Optimization for Multilingual Adverse Drug Event Detection (Singh, SMM4H 2026)

ACL

• Ankit Kumar Singh. 2026. Gladiators at #SMM4H–HeaRD 2026: Multi-Seed XLM-RoBERTa Ensemble with Focal Loss and Per-Language Threshold Optimization for Multilingual Adverse Drug Event Detection. In Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks, pages 7–11, San Diego, United States. Association for Computational Linguistics.