IntelligenceLab/VideoHallu

Tasks

• visual-question-answering

Citation text from the card

@misc{li2025videohalluevaluatingmitigatingmultimodal,
      title={VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for Synthetic Videos}, 
      author={Zongxia Li and Xiyang Wu and Yubin Qin and Guangyao Shi and Hongyang Du and Dinesh Manocha and Tianyi Zhou and Jordan Lee Boyd-Graber},
      year={2025},
      eprint={2505.01481},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2505.01481}, 
}


@misc{li2025surveystateartlarge,
      title={A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges}, 
      author={Zongxia Li and Xiyang Wu and Hongyang Du and Fuxiao Liu and Huy Nghiem and Guangyao Shi},
      year={2025},
      eprint={2501.02189},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2501.02189}, 
}

@misc{guan2024hallusionbenchadvanceddiagnosticsuite,
      title={HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models}, 
      author={Tianrui Guan and Fuxiao Liu and Xiyang Wu and Ruiqi Xian and Zongxia Li and Xiaoyu Liu and Xijun Wang and Lichang Chen and Furong Huang and Yaser Yacoob and Dinesh Manocha and Tianyi Zhou},
      year={2024},
      eprint={2310.14566},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2310.14566}, 
}

@misc{wu2024autohallusionautomaticgenerationhallucination,
      t

All datasets marked Permissive or share-alike | JSON