@inproceedings{wang-etal-2026-sparsealign,
title = "{S}parse{A}lign-{OOC}: Auditing News Image-Text Out-of-Context Detection with Sparse Autoencoders",
author = "Wang, Guoxin and
Liu, Junjie and
Chen, Shaowu",
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.291/",
pages = "6193--6207",
ISBN = "979-8-89176-462-0",
abstract = "Out-of-context (OOC) misinformation often arises when an authentic news image is paired with misleading text, making the cross-modal evidence used by a detector an important object of interpretation. We present SparseAlign-OOC, a two-level sparse autoencoder (SAE) framework for auditing NewsCLIPpings CLIP-embedding detectors through recurring image-text alignment features. A pair-space SAE maps detector inputs into sparse coordinates whose high-activation examples form human-auditable concept groups, while a hidden-state SAE traces sparse features associated with detector decisions. In a 250-item blind human audit with three annotators, selected SAE groups yield 18/50 coherent-alignment concepts, compared with 9/50 for prototype clustering, 7/50 for PCA, 4/50 for a dense autoencoder, and 0/50 for random groups. A 150-item replication audit on a stronger deep MLP preserves the same ordering, producing pooled results of 29/80 SAE alignment groups versus 15/80 for the strongest baseline. Coverage analysis shows that the presence of concepts increases with activation strength. In contrast, direct pair-space interventions show that human-labeled alignment features produce larger detector changes than topical, incoherent, or random SAE features. In the NewsCLIPpings CLIP-embedding setting, SparseAlign-OOC provides a validated audit pipeline for exposing recurring alignment factors that are both human-auditable and functionally connected to detector behavior."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-sparsealign">
<titleInfo>
<title>SparseAlign-OOC: Auditing News Image-Text Out-of-Context Detection with Sparse Autoencoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guoxin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaowu</namePart>
<namePart type="family">Chen</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>Out-of-context (OOC) misinformation often arises when an authentic news image is paired with misleading text, making the cross-modal evidence used by a detector an important object of interpretation. We present SparseAlign-OOC, a two-level sparse autoencoder (SAE) framework for auditing NewsCLIPpings CLIP-embedding detectors through recurring image-text alignment features. A pair-space SAE maps detector inputs into sparse coordinates whose high-activation examples form human-auditable concept groups, while a hidden-state SAE traces sparse features associated with detector decisions. In a 250-item blind human audit with three annotators, selected SAE groups yield 18/50 coherent-alignment concepts, compared with 9/50 for prototype clustering, 7/50 for PCA, 4/50 for a dense autoencoder, and 0/50 for random groups. A 150-item replication audit on a stronger deep MLP preserves the same ordering, producing pooled results of 29/80 SAE alignment groups versus 15/80 for the strongest baseline. Coverage analysis shows that the presence of concepts increases with activation strength. In contrast, direct pair-space interventions show that human-labeled alignment features produce larger detector changes than topical, incoherent, or random SAE features. In the NewsCLIPpings CLIP-embedding setting, SparseAlign-OOC provides a validated audit pipeline for exposing recurring alignment factors that are both human-auditable and functionally connected to detector behavior.</abstract>
<identifier type="citekey">wang-etal-2026-sparsealign</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.291/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>6193</start>
<end>6207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SparseAlign-OOC: Auditing News Image-Text Out-of-Context Detection with Sparse Autoencoders
%A Wang, Guoxin
%A Liu, Junjie
%A Chen, Shaowu
%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 wang-etal-2026-sparsealign
%X Out-of-context (OOC) misinformation often arises when an authentic news image is paired with misleading text, making the cross-modal evidence used by a detector an important object of interpretation. We present SparseAlign-OOC, a two-level sparse autoencoder (SAE) framework for auditing NewsCLIPpings CLIP-embedding detectors through recurring image-text alignment features. A pair-space SAE maps detector inputs into sparse coordinates whose high-activation examples form human-auditable concept groups, while a hidden-state SAE traces sparse features associated with detector decisions. In a 250-item blind human audit with three annotators, selected SAE groups yield 18/50 coherent-alignment concepts, compared with 9/50 for prototype clustering, 7/50 for PCA, 4/50 for a dense autoencoder, and 0/50 for random groups. A 150-item replication audit on a stronger deep MLP preserves the same ordering, producing pooled results of 29/80 SAE alignment groups versus 15/80 for the strongest baseline. Coverage analysis shows that the presence of concepts increases with activation strength. In contrast, direct pair-space interventions show that human-labeled alignment features produce larger detector changes than topical, incoherent, or random SAE features. In the NewsCLIPpings CLIP-embedding setting, SparseAlign-OOC provides a validated audit pipeline for exposing recurring alignment factors that are both human-auditable and functionally connected to detector behavior.
%U https://aclanthology.org/2026.findings-emnlp.291/
%P 6193-6207
Markdown (Informal)
[SparseAlign-OOC: Auditing News Image-Text Out-of-Context Detection with Sparse Autoencoders](https://aclanthology.org/2026.findings-emnlp.291/) (Wang et al., Findings 2026)
ACL