@inproceedings{mukherjee-etal-2026-spur,
title = "{SPUR}-{XMC}: Context-Adaptive Spurious Correlation Mitigation for Extreme Multi-Label Classification of Biomedical Literature",
author = "Mukherjee, Ratri and
Dahal, Shailesh and
Jha, Kishlay",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1597/",
doi = "10.18653/2026.findings-emnlp.1597",
pages = "34025--34045",
ISBN = "979-8-89176-462-0",
abstract = "Extreme multi-label text classification (XMTC) of biomedical literature aims to classify articles into a set of pre-defined labels from a large and highly skewed label distribution space. While recent pretrained language model (PLM)-based XMTC approaches have made substantial advances, they still struggle to generalize to tail labels representing concepts of high biomedical significance (e.g., rare diseases). A key factor contributing to poor tail-label performance is the presence of spurious correlations, where models inadvertently learn non-informative feature-label associations. To address this issue, we propose a novel context-adaptive spurious correlation mitigation technique, SPUR-XMC, which selectively attenuates spurious influences according to the context of the input article. A unique advantage of the proposed framework is that it does not modify existing PLM architectures for XMTC and instead operates as an add-on enhancement module. Extensive experiments across benchmark biomedical literature datasets demonstrate the effectiveness of the proposed approach."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mukherjee-etal-2026-spur">
<titleInfo>
<title>SPUR-XMC: Context-Adaptive Spurious Correlation Mitigation for Extreme Multi-Label Classification of Biomedical Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ratri</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shailesh</namePart>
<namePart type="family">Dahal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kishlay</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Extreme multi-label text classification (XMTC) of biomedical literature aims to classify articles into a set of pre-defined labels from a large and highly skewed label distribution space. While recent pretrained language model (PLM)-based XMTC approaches have made substantial advances, they still struggle to generalize to tail labels representing concepts of high biomedical significance (e.g., rare diseases). A key factor contributing to poor tail-label performance is the presence of spurious correlations, where models inadvertently learn non-informative feature-label associations. To address this issue, we propose a novel context-adaptive spurious correlation mitigation technique, SPUR-XMC, which selectively attenuates spurious influences according to the context of the input article. A unique advantage of the proposed framework is that it does not modify existing PLM architectures for XMTC and instead operates as an add-on enhancement module. Extensive experiments across benchmark biomedical literature datasets demonstrate the effectiveness of the proposed approach.</abstract>
<identifier type="citekey">mukherjee-etal-2026-spur</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1597</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1597/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>34025</start>
<end>34045</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPUR-XMC: Context-Adaptive Spurious Correlation Mitigation for Extreme Multi-Label Classification of Biomedical Literature
%A Mukherjee, Ratri
%A Dahal, Shailesh
%A Jha, Kishlay
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F mukherjee-etal-2026-spur
%X Extreme multi-label text classification (XMTC) of biomedical literature aims to classify articles into a set of pre-defined labels from a large and highly skewed label distribution space. While recent pretrained language model (PLM)-based XMTC approaches have made substantial advances, they still struggle to generalize to tail labels representing concepts of high biomedical significance (e.g., rare diseases). A key factor contributing to poor tail-label performance is the presence of spurious correlations, where models inadvertently learn non-informative feature-label associations. To address this issue, we propose a novel context-adaptive spurious correlation mitigation technique, SPUR-XMC, which selectively attenuates spurious influences according to the context of the input article. A unique advantage of the proposed framework is that it does not modify existing PLM architectures for XMTC and instead operates as an add-on enhancement module. Extensive experiments across benchmark biomedical literature datasets demonstrate the effectiveness of the proposed approach.
%R 10.18653/2026.findings-emnlp.1597
%U https://aclanthology.org/2026.findings-emnlp.1597/
%U https://doi.org/10.18653/2026.findings-emnlp.1597
%P 34025-34045
Markdown (Informal)
[SPUR-XMC: Context-Adaptive Spurious Correlation Mitigation for Extreme Multi-Label Classification of Biomedical Literature](https://aclanthology.org/2026.findings-emnlp.1597/) (Mukherjee et al., Findings 2026)
ACL