@inproceedings{narayan-2026-alphastream,
title = "Alphastream at {C}hild{S}afe{A}ds 2026: Gated Per-Label Merging and an Advertiser-Precedent Rule for Rare Compliance Classes",
author = "Narayan, Raghavendra Prasad",
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-1.8/",
pages = "64--75",
ISBN = "979-8-89176-494-1",
abstract = "We describe our system for ChildSafeAds 2026, the shared task on commercial content in child-facing YouTube videos: it labels each sponsored segment for commercial type (ST1), product category (ST2) and EU compliance flags (ST3). A multi-task ModernBERT-large encoder and an entailment-style reformulation of the compliance subtask supply seed-averaged probabilities, merged label by label under a paired bootstrap and a dev-to-test count check. Inference uses eight fine-tuned encoders and no generative model; the 503 test instances are estimated at under one GPU-hour, and all experiments cost about US$17. It scored 0.7645 mean macro-F1 on development and 0.6798 on test, 0.046 of it from a rule keyed on advertiser identity for one ST1 class absent from development. Our official entry, a variant using one leaderboard probe, scored 0.7022, fourth of 21 teams. A single-seed ablation values the four access levels at +0.042, against +0.128 from encoder scale. We also report five negative results, among them seed variance matching our largest modelling gains, synthetic data helping one architecture and breaking the other, and 21\% more training data lowering the test score; separately, near-duplicate training instances agree on the full flag set only 43–63\% of the time, often on identical cited evidence.$"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="narayan-2026-alphastream">
<titleInfo>
<title>Alphastream at ChildSafeAds 2026: Gated Per-Label Merging and an Advertiser-Precedent Rule for Rare Compliance Classes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raghavendra</namePart>
<namePart type="given">Prasad</namePart>
<namePart type="family">Narayan</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 our system for ChildSafeAds 2026, the shared task on commercial content in child-facing YouTube videos: it labels each sponsored segment for commercial type (ST1), product category (ST2) and EU compliance flags (ST3). A multi-task ModernBERT-large encoder and an entailment-style reformulation of the compliance subtask supply seed-averaged probabilities, merged label by label under a paired bootstrap and a dev-to-test count check. Inference uses eight fine-tuned encoders and no generative model; the 503 test instances are estimated at under one GPU-hour, and all experiments cost about US17. It scored 0.7645 mean macro-F1 on development and 0.6798 on test, 0.046 of it from a rule keyed on advertiser identity for one ST1 class absent from development. Our official entry, a variant using one leaderboard probe, scored 0.7022, fourth of 21 teams. A single-seed ablation values the four access levels at +0.042, against +0.128 from encoder scale. We also report five negative results, among them seed variance matching our largest modelling gains, synthetic data helping one architecture and breaking the other, and 21% more training data lowering the test score; separately, near-duplicate training instances agree on the full flag set only 43–63% of the time, often on identical cited evidence.</abstract>
<identifier type="citekey">narayan-2026-alphastream</identifier>
<location>
<url>https://aclanthology.org/2026.nllp-1.8/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>64</start>
<end>75</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alphastream at ChildSafeAds 2026: Gated Per-Label Merging and an Advertiser-Precedent Rule for Rare Compliance Classes
%A Narayan, Raghavendra Prasad
%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 narayan-2026-alphastream
%X We describe our system for ChildSafeAds 2026, the shared task on commercial content in child-facing YouTube videos: it labels each sponsored segment for commercial type (ST1), product category (ST2) and EU compliance flags (ST3). A multi-task ModernBERT-large encoder and an entailment-style reformulation of the compliance subtask supply seed-averaged probabilities, merged label by label under a paired bootstrap and a dev-to-test count check. Inference uses eight fine-tuned encoders and no generative model; the 503 test instances are estimated at under one GPU-hour, and all experiments cost about US17. It scored 0.7645 mean macro-F1 on development and 0.6798 on test, 0.046 of it from a rule keyed on advertiser identity for one ST1 class absent from development. Our official entry, a variant using one leaderboard probe, scored 0.7022, fourth of 21 teams. A single-seed ablation values the four access levels at +0.042, against +0.128 from encoder scale. We also report five negative results, among them seed variance matching our largest modelling gains, synthetic data helping one architecture and breaking the other, and 21% more training data lowering the test score; separately, near-duplicate training instances agree on the full flag set only 43–63% of the time, often on identical cited evidence.
%U https://aclanthology.org/2026.nllp-1.8/
%P 64-75
Markdown (Informal)
[Alphastream at ChildSafeAds 2026: Gated Per-Label Merging and an Advertiser-Precedent Rule for Rare Compliance Classes](https://aclanthology.org/2026.nllp-1.8/) (Narayan, NLLP 2026)
ACL