残差解码：通过历史感知残差引导减轻大视觉-语言模型中的幻觉
Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
AI总结：
本文提出残差解码方法，通过利用历史信息辅助解码，纠正大视觉-语言模型中的语言先验偏差，有效抑制幻觉并提升视觉接地能力。
摘要：
大型视觉-语言模型（LVLMs）能够从图像-文本输入中推理并在各种多模态任务中表现良好。尽管取得了成功，但它们受到语言先验的影响，常常产生幻觉。幻觉指的是生成的内容在语法和句法上一致，但与视觉输入无匹配或直接相关。为了解决这个问题，我们提出了残差解码（ResDec）。它是一种新的无训练方法，利用历史信息来辅助解码。该方法依赖于LVLMs内部的隐含推理机制和token logit演变机制来纠正偏差。广泛的实验表明，ResDec有效抑制了由语言先验引起的幻觉，显著提高了视觉接地能力，并减少了物体幻觉。除了减轻幻觉外，ResDec还在全面的LVLM基准测试中表现优异，突显了其广泛的应用性。
英文摘要：
Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and often produce hallucinations. Hallucinations denote generated content that is grammatically and syntactically coherent, yet bears no match or direct relevance to visual input. To address this problem, we propose Residual Decoding (ResDec). It is a novel training-free method that uses historical information to aid decoding. The method relies on the internal implicit reasoning mechanism and token logits evolution mechanism of LVLMs to correct biases. Extensive experiments demonstrate that ResDec effectively suppresses hallucinations induced by language priors, significantly improves visual grounding, and reduces object hallucinations. In addition to mitigating hallucinations, ResDec also performs exceptionally well on comprehensive LVLM benchmarks, highlighting its broad applicability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
