@inproceedings{ji-etal-2025-raven-pinpointing,
    title = "{RAVEN}++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning",
    author = "Ji, Deyi  and
      Yang, Yuekui  and
      Liu, Liqun  and
      Shu, Peng  and
      Wu, Haiyang  and
      Tang, Shaogang  and
      Chen, Xudong  and
      Ma, Shaoping  and
      Chen, Tianrun  and
      Zhu, Lanyun",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.1/",
    pages = "1--10",
    ISBN = "979-8-89176-333-3",
    abstract = "Advertising (Ad) is a cornerstone of the digital economy, yet the moderation of video advertisements remains a significant challenge due to their complexity and the need for precise violation localization. While recent advancements, such as the RAVEN model, have improved coarse-grained violation detection, critical gaps persist in fine-grained understanding, explainability, and generalization. To address these limitations, we propose RAVEN++, a novel framework that introduces three key innovations: 1) Active Reinforcement Learning (RL), which dynamically adapts training to samples of varying difficulty; 2) Fine-Grained Violation Understanding, achieved through hierarchical reward functions and reasoning distillation; and 3) Progressive Multi-Stage Training, which systematically combines knowledge injection, curriculum-based passive RL, and active RL. Extensive experiments on both public and proprietary datasets, on both offline scenarios and online deployed A/B Testing, demonstrate that RAVEN++ outperforms general-purpose LLMs and specialized models like RAVEN in terms of fine-grained violation understanding, reasoning capabilities, and generalization ability."
}