让大模型更懂审核规则，通过提问链提升短视频内容判别力
IPS: In-Prompt Process Supervision for Short Video Content Moderation
- 在微调时引入问答链引导模型逐步推理
- 在多个数据集上超越基线模型，性能稳定
- 用模型自动生成标签也效果接近人工，适合大规模应用
多模态大模型能有效捕捉短视频语义，但常忽略审核政策中的细节。为此，我们提出IPS框架，在微调阶段引入辅助问题的序列推理，实现提示内过程监督。IPS在公开与私有基准上持续优于基线模型。将人工标注的辅助标签替换为模型生成标签后，性能仅轻微下降，证明其对噪声标注鲁棒且可扩展。该方法为工业级大规模多模态分类提供了高效可靠的解决方案。
原文摘要 · Abstract (English)
Multimodal large language models (MLLMs) are effective at capturing the semantics of short video content; however, they often fail to attend to the policy-specific details required for reliable content moderation. To address this limitation, we introduce IPS, a novel framework that integrates In-prompt Process Supervision into MLLMs by introducing sequential reasoning over ancillary questions during fine-tuning. IPS consistently outperforms baseline MLLMs on public and proprietary benchmarks. Moreover, replacing human-annotated ancillary labels with MLLM-generated ones results in only marginal performance degradation, demonstrating robustness to noisy supervision and strong scalability with model-generated annotations. These findings establish IPS as a scalable and effective solution for complex multimodal classification in large-scale industrial settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。