@inproceedings{chen-etal-2026-r3,
title = "$\mathcal{R}^3$: Advertisement Compliance $\mathcal{R}$ectification via Group-$\mathcal{R}$elative Experience Extractor and Curriculum $\mathcal{R}$einforcement",
author = "Chen, Yuan and
Hu, Zhenyu and
Xue, Mengge and
Te, Cao and
Liu, Liqun and
Shu, Peng and
Yu, Huan and
Jiang, Jie",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.24/",
doi = "10.18653/v1/2026.acl-industry.24",
pages = "358--370",
ISBN = "979-8-89176-394-4",
abstract = "Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements.However, existing safety-driven methods often suffer from aggressive over-editing, which compromises the advertiser{'}s original semantic intent merely to satisfy compliance.In this work, we target the rectification of textual violations in video ads, covering both speech transcripts and on-screen text. We propose $\mathcal{R}^3$, a novel framework designed to harmonize compliance with original semantic intent preservation.Our approach integrates three key innovations: (1) an experience-driven data synthesis framework that bootstraps high-quality supervision via group-\textbf{R}elative compliance experience extractor; (2) a curriculum \textbf{R}einforcement learning strategy with hierarchical rewards designed to enforce compliance while maximizing semantic consistency;and (3) a comprehensive video \textbf{R}ectification framework seamlessly integrating text recognition, rewriting, and re-rendering for industrial deployment. Extensive experiments on industrial datasets and online A/B testing demonstrate that $\mathcal{R}^3$ significantly outperforms state-of-the-art baselines, achieving an optimal trade-off between violation rectification and intent preservation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-r3">
<titleInfo>
<title>\mathcalR³: Advertisement Compliance \mathcalRectification via Group-\mathcalRelative Experience Extractor and Curriculum \mathcalReinforcement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenyu</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengge</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cao</namePart>
<namePart type="family">Te</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Jiang</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 (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</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, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements.However, existing safety-driven methods often suffer from aggressive over-editing, which compromises the advertiser’s original semantic intent merely to satisfy compliance.In this work, we target the rectification of textual violations in video ads, covering both speech transcripts and on-screen text. We propose \mathcalR³, a novel framework designed to harmonize compliance with original semantic intent preservation.Our approach integrates three key innovations: (1) an experience-driven data synthesis framework that bootstraps high-quality supervision via group-Relative compliance experience extractor; (2) a curriculum Reinforcement learning strategy with hierarchical rewards designed to enforce compliance while maximizing semantic consistency;and (3) a comprehensive video Rectification framework seamlessly integrating text recognition, rewriting, and re-rendering for industrial deployment. Extensive experiments on industrial datasets and online A/B testing demonstrate that \mathcalR³ significantly outperforms state-of-the-art baselines, achieving an optimal trade-off between violation rectification and intent preservation.</abstract>
<identifier type="citekey">chen-etal-2026-r3</identifier>
<identifier type="doi">10.18653/v1/2026.acl-industry.24</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.24/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>358</start>
<end>370</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T \mathcalR³: Advertisement Compliance \mathcalRectification via Group-\mathcalRelative Experience Extractor and Curriculum \mathcalReinforcement
%A Chen, Yuan
%A Hu, Zhenyu
%A Xue, Mengge
%A Te, Cao
%A Liu, Liqun
%A Shu, Peng
%A Yu, Huan
%A Jiang, Jie
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F chen-etal-2026-r3
%X Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements.However, existing safety-driven methods often suffer from aggressive over-editing, which compromises the advertiser’s original semantic intent merely to satisfy compliance.In this work, we target the rectification of textual violations in video ads, covering both speech transcripts and on-screen text. We propose \mathcalR³, a novel framework designed to harmonize compliance with original semantic intent preservation.Our approach integrates three key innovations: (1) an experience-driven data synthesis framework that bootstraps high-quality supervision via group-Relative compliance experience extractor; (2) a curriculum Reinforcement learning strategy with hierarchical rewards designed to enforce compliance while maximizing semantic consistency;and (3) a comprehensive video Rectification framework seamlessly integrating text recognition, rewriting, and re-rendering for industrial deployment. Extensive experiments on industrial datasets and online A/B testing demonstrate that \mathcalR³ significantly outperforms state-of-the-art baselines, achieving an optimal trade-off between violation rectification and intent preservation.
%R 10.18653/v1/2026.acl-industry.24
%U https://aclanthology.org/2026.acl-industry.24/
%U https://doi.org/10.18653/v1/2026.acl-industry.24
%P 358-370
Markdown (Informal)
[ℛ3: Advertisement Compliance ℛectification via Group-ℛelative Experience Extractor and Curriculum ℛeinforcement](https://aclanthology.org/2026.acl-industry.24/) (Chen et al., ACL 2026)
ACL
- Yuan Chen, Zhenyu Hu, Mengge Xue, Cao Te, Liqun Liu, Peng Shu, Huan Yu, and Jie Jiang. 2026. ℛ3: Advertisement Compliance ℛectification via Group-ℛelative Experience Extractor and Curriculum ℛeinforcement. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 358–370, San Diego, California, USA. Association for Computational Linguistics.