@inproceedings{zhang-etal-2026-cultivating,
    title = "Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection",
    author = "Zhang, Yuchen  and
      Wang, Yaxiong  and
      Han, Kecheng  and
      Wu, Yujiao  and
      Wu, Lianwei  and
      Zhu, Li  and
      Zheng, Zhedong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1316/",
    pages = "28545--28560",
    ISBN = "979-8-89176-390-6",
    abstract = "Recent advances in generative AI have significantly enhanced the realism of multimodal media manipulation, thereby posing substantial challenges to manipulation detection. Existing manipulation detection and grounding approaches predominantly focus on manipulation type classification under result-oriented supervision, which not only lacks interpretability but also tends to overfit superficial artifacts. In this paper, we argue that generalizable detection requires incorporating explicit forensic reasoning, rather than merely classifying a limited set of manipulation types, which fails to generalize to unseen manipulation patterns. To this end, we propose **REFORM**, a reasoning-driven framework that shifts learning from outcome fitting to process modeling. REFORM adopts a three-stage curriculum that first induces forensic rationales, then aligns reasoning with final judgments, and finally refines logical consistency via reinforcement learning. To support this paradigm, we introduce **ROM**, a large-scale dataset with rich reasoning annotations. Extensive experiments show that REFORM establishes new state-of-the-art performance with superior generalization, achieving 81.52{\%} ACC on ROM, 76.65{\%} ACC on DGM4, and 74.9 F1 on MMFakeBench."
}