| name | r3-advertisement-compliance-rectification-via-group-relative-experience |
| description | 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. Howe. Based on arXiv:2607.07318. |
R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement
arXiv: 2607.07318 | Authors: Yuan Chen, Zhenyu Hu, Mengge Xue, Te Cao, Liqun Liu et al. | Utility: 0.85
Overview
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 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 a 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 R^3 significantly outperforms state-of-the-art baselines, achieving an optimal trade-off between violation rectification and intent preservation.
Key Contributions
- 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.
Implementation Notes
- Keywords: reinforcement-learning, ai-safety
- Categories: cs.CL, cs.LG
- Published: 2026-07-08
Activation Criteria
Use this skill when working on tasks involving: reinforcement-learning, ai-safety.
