@inproceedings{liu-etal-2026-ips,
    title = "{IPS}: In-Prompt Process Supervision for Short Video Content Moderation",
    author = "Liu, Mingchao  and
      Sun, Yu  and
      Sun, Ruixiao  and
      Dong, Xin  and
      Shen, Xiang  and
      Wang, Hongwei  and
      Xiong, Hongyu  and
      Song, Yang",
    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 ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.89/",
    pages = "1277--1288",
    ISBN = "979-8-89176-394-4",
    abstract = "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."
}