2026.acl-industry.24@ACL

Total: 1

#1 ℛ3: Advertisement Compliance ℛectification via Group-ℛelative Experience Extractor and Curriculum ℛeinforcement [PDF] [Copy] [Kimi] [REL]

Authors: Yuan Chen, Zhenyu Hu, Mengge Xue, Cao Te, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang

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 ℛ3, 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 ℛ3 significantly outperforms state-of-the-art baselines, achieving an optimal trade-off between violation rectification and intent preservation.

Subject: ACL.2026 - Industry Track