@inproceedings{guillermo-etal-2026-thesis,
title = "Thesis Proposal: An Explainable Multimodal Framework for Detecting Harmful Content in Code-Switched Children{'}s Media",
author = "Guillermo, Juliana Isabelle A. and
Catapang, Jasper Kyle and
Oco, Nathaniel",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.40/",
pages = "450--462",
ISBN = "979-8-89176-393-7",
abstract = "Current automated content moderation systems fail to protect children from harmful YouTube content, particularly in under-resourced, code-switched settings. These systems are often text-only, English-centric, and operate as `black boxes,' lacking the multimodal understanding and transparency needed for effective moderation. This thesis proposes a novel hybrid framework for the explainable multimodal detection of harmful content in videos with code-switching. The proposed framework integrates a fine-tuned classifier for accurate, scalable detection with an LLM-powered module that synthesizes the classifier{'}s internal evidential signals (e.g., text attention and visual heat maps) to generate faithful, human-readable rationales for each decision. As a primary case study, the framework will be developed and validated on an English{--}Filipino code-switched dataset. Expected contributions include a new dataset publicly available under controlled access (de-identified transcripts, blacked-out frames, extracted feature representations, and metadata via data-sharing agreement) and a blueprint for building more equitable, transparent, and trustworthy AI safety systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guillermo-etal-2026-thesis">
<titleInfo>
<title>Thesis Proposal: An Explainable Multimodal Framework for Detecting Harmful Content in Code-Switched Children’s Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juliana</namePart>
<namePart type="given">Isabelle</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Guillermo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jasper</namePart>
<namePart type="given">Kyle</namePart>
<namePart type="family">Catapang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</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 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>Current automated content moderation systems fail to protect children from harmful YouTube content, particularly in under-resourced, code-switched settings. These systems are often text-only, English-centric, and operate as ‘black boxes,’ lacking the multimodal understanding and transparency needed for effective moderation. This thesis proposes a novel hybrid framework for the explainable multimodal detection of harmful content in videos with code-switching. The proposed framework integrates a fine-tuned classifier for accurate, scalable detection with an LLM-powered module that synthesizes the classifier’s internal evidential signals (e.g., text attention and visual heat maps) to generate faithful, human-readable rationales for each decision. As a primary case study, the framework will be developed and validated on an English–Filipino code-switched dataset. Expected contributions include a new dataset publicly available under controlled access (de-identified transcripts, blacked-out frames, extracted feature representations, and metadata via data-sharing agreement) and a blueprint for building more equitable, transparent, and trustworthy AI safety systems.</abstract>
<identifier type="citekey">guillermo-etal-2026-thesis</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.40/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>450</start>
<end>462</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thesis Proposal: An Explainable Multimodal Framework for Detecting Harmful Content in Code-Switched Children’s Media
%A Guillermo, Juliana Isabelle A.
%A Catapang, Jasper Kyle
%A Oco, Nathaniel
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F guillermo-etal-2026-thesis
%X Current automated content moderation systems fail to protect children from harmful YouTube content, particularly in under-resourced, code-switched settings. These systems are often text-only, English-centric, and operate as ‘black boxes,’ lacking the multimodal understanding and transparency needed for effective moderation. This thesis proposes a novel hybrid framework for the explainable multimodal detection of harmful content in videos with code-switching. The proposed framework integrates a fine-tuned classifier for accurate, scalable detection with an LLM-powered module that synthesizes the classifier’s internal evidential signals (e.g., text attention and visual heat maps) to generate faithful, human-readable rationales for each decision. As a primary case study, the framework will be developed and validated on an English–Filipino code-switched dataset. Expected contributions include a new dataset publicly available under controlled access (de-identified transcripts, blacked-out frames, extracted feature representations, and metadata via data-sharing agreement) and a blueprint for building more equitable, transparent, and trustworthy AI safety systems.
%U https://aclanthology.org/2026.acl-srw.40/
%P 450-462
Markdown (Informal)
[Thesis Proposal: An Explainable Multimodal Framework for Detecting Harmful Content in Code-Switched Children’s Media](https://aclanthology.org/2026.acl-srw.40/) (Guillermo et al., ACL 2026)
ACL