@inproceedings{ge-etal-2025-mrfd,
    title = "{MRFD}: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in {LVLM}s",
    author = "Ge, Haonan  and
      Wang, Yiwei  and
      Yang, Ming-Hsuan  and
      Cai, Yujun",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.858/",
    doi = "10.18653/v1/2025.findings-emnlp.858",
    pages = "15860--15879",
    ISBN = "979-8-89176-335-7",
    abstract = "Large Vision-Language Models (LVLMs) have shown strong performance across multimodal tasks. However, they often produce hallucinations{---}text that is inconsistent with visual input, due to the limited ability to verify information in different regions of the image. To address this, we propose **Multi-Region Fusion Decoding (MRFD)**, a training-free decoding method that improves factual grounding by modeling inter-region consistency. MRFD identifies salient regions using cross-attention, generates initial responses for each, and computes reliability weights based on Jensen-Shannon Divergence (JSD) among the responses. These weights guide a consistency-aware fusion of per-region predictions, using region-aware prompts inspired by Chain-of-Thought reasoning. Experiments across multiple LVLMs and benchmarks show that MRFD significantly reduces hallucinations and improves response factuality without requiring model updates."
}