@inproceedings{sahoo-etal-2026-ai,
title = "{AI}-Monitors at {C}hild{S}afe{A}ds 2026: A Routed Hybrid for Commercial Content in Child-Facing {Y}ou{T}ube Videos",
author = "sahoo, Pragyananda and
Tripathi, Vishnu and
joshi, Prakhar and
Kumar, Gaurav and
Mani, Neel",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goanț{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preoțiuc-Pietro, Daniel and
Spanakis, Gerasimos and
Xu, Shanshan",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nllp-1.23/",
pages = "259--270",
ISBN = "979-8-89176-494-1",
abstract = "We describe AI-Monitors, our system for the ChildSafeAds shared task at NLLP@EMNLP 2026. The task labels sponsored segments in YouTube videos aimed at teenagers with their commercial type, product category and compliance-risk flags, and provides the input at four levels of increasing collection cost, from the free transcript to a crawled product page. Our system gives each sub-task its own input level and model: a fine-tuned ModernBERT-large encoder reading all four levels predicts commercial type and product category, the latter averaged with a TF-IDF classifier; a second encoder reading only the transcript predicts the compliance flags, averaged on the two disclosure flags with a QLoRA-tuned Qwen2.5-7B-Instruct that also reads the video metadata, before rules from the task{'}s taxonomy are applied. The system scored 0.6223 mean macro-F1 on the test set, 11th of 21 teams, and labels the 503 test instances in 25.5 GPU-minutes. We report the experiments behind each design choice: in our runs the crawled page helped product categorisation but not compliance flagging, the taxonomy{'}s definitions helped a prompted model while the legal provisions added little, and in two cases our validation procedure was misleading."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sahoo-etal-2026-ai">
<titleInfo>
<title>AI-Monitors at ChildSafeAds 2026: A Routed Hybrid for Commercial Content in Child-Facing YouTube Videos</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pragyananda</namePart>
<namePart type="family">sahoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishnu</namePart>
<namePart type="family">Tripathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prakhar</namePart>
<namePart type="family">joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neel</namePart>
<namePart type="family">Mani</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>Proceedings of the Natural Legal Language Processing Workshop 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goanță</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoțiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Xu</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">979-8-89176-494-1</identifier>
</relatedItem>
<abstract>We describe AI-Monitors, our system for the ChildSafeAds shared task at NLLP@EMNLP 2026. The task labels sponsored segments in YouTube videos aimed at teenagers with their commercial type, product category and compliance-risk flags, and provides the input at four levels of increasing collection cost, from the free transcript to a crawled product page. Our system gives each sub-task its own input level and model: a fine-tuned ModernBERT-large encoder reading all four levels predicts commercial type and product category, the latter averaged with a TF-IDF classifier; a second encoder reading only the transcript predicts the compliance flags, averaged on the two disclosure flags with a QLoRA-tuned Qwen2.5-7B-Instruct that also reads the video metadata, before rules from the task’s taxonomy are applied. The system scored 0.6223 mean macro-F1 on the test set, 11th of 21 teams, and labels the 503 test instances in 25.5 GPU-minutes. We report the experiments behind each design choice: in our runs the crawled page helped product categorisation but not compliance flagging, the taxonomy’s definitions helped a prompted model while the legal provisions added little, and in two cases our validation procedure was misleading.</abstract>
<identifier type="citekey">sahoo-etal-2026-ai</identifier>
<location>
<url>https://aclanthology.org/2026.nllp-1.23/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>259</start>
<end>270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AI-Monitors at ChildSafeAds 2026: A Routed Hybrid for Commercial Content in Child-Facing YouTube Videos
%A sahoo, Pragyananda
%A Tripathi, Vishnu
%A joshi, Prakhar
%A Kumar, Gaurav
%A Mani, Neel
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%Y Xu, Shanshan
%S Proceedings of the Natural Legal Language Processing Workshop 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-494-1
%F sahoo-etal-2026-ai
%X We describe AI-Monitors, our system for the ChildSafeAds shared task at NLLP@EMNLP 2026. The task labels sponsored segments in YouTube videos aimed at teenagers with their commercial type, product category and compliance-risk flags, and provides the input at four levels of increasing collection cost, from the free transcript to a crawled product page. Our system gives each sub-task its own input level and model: a fine-tuned ModernBERT-large encoder reading all four levels predicts commercial type and product category, the latter averaged with a TF-IDF classifier; a second encoder reading only the transcript predicts the compliance flags, averaged on the two disclosure flags with a QLoRA-tuned Qwen2.5-7B-Instruct that also reads the video metadata, before rules from the task’s taxonomy are applied. The system scored 0.6223 mean macro-F1 on the test set, 11th of 21 teams, and labels the 503 test instances in 25.5 GPU-minutes. We report the experiments behind each design choice: in our runs the crawled page helped product categorisation but not compliance flagging, the taxonomy’s definitions helped a prompted model while the legal provisions added little, and in two cases our validation procedure was misleading.
%U https://aclanthology.org/2026.nllp-1.23/
%P 259-270
Markdown (Informal)
[AI-Monitors at ChildSafeAds 2026: A Routed Hybrid for Commercial Content in Child-Facing YouTube Videos](https://aclanthology.org/2026.nllp-1.23/) (sahoo et al., NLLP 2026)
ACL