@inproceedings{zhao-etal-2025-hallucination,
    title = "Can Hallucination Correction Improve Video-Language Alignment?",
    author = "Zhao, Lingjun  and
      Xie, Mingyang  and
      Cascante-Bonilla, Paola  and
      Iii, Hal Daum{\'e}  and
      Lee, Kwonjoon",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.1314/",
    pages = "25636--25646",
    ISBN = "979-8-89176-256-5",
    abstract = "Large Vision-Language Models often generate hallucinated content that is not grounded in its visual inputs. While prior work focuses on mitigating hallucinations, we instead explore leveraging hallucination correction as a training objective to improve video-language alignment. We introduce HACA, a self-training framework learning to correct hallucinations in descriptions that do not align with the video content. By identifying and correcting inconsistencies, HACA enhances the model{'}s ability to align video and textual representations for spatio-temporal reasoning. Our experimental results show consistent gains in video-caption binding and text-to-video retrieval tasks, demonstrating that hallucination correction-inspired tasks serve as an effective strategy for improving vision and language alignment."
}