事实性水印：通过三层对比解码引导视觉语言模型走向真实
Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
AI总结：
提出无需训练的三层对比解码加水印方法，通过选择成熟层、业余层和枢轴层，减少视觉语言模型幻觉，在POPE、MME和AMBER基准上达到最先进性能。
摘要：
大型视觉语言模型（LVLMs）近年来在各种多模态任务上展现出令人瞩目的成果，甚至在某些情况下达到了与人类相当的性能。然而，LVLMs仍然容易产生幻觉——它们常常过度依赖单一模态或记忆训练数据，而没有适当地将其输出与视觉信息进行 grounding（ grounding，即基于视觉证据的锚定）。为了解决这一问题，我们提出了一种无需训练的、带水印的三层对比解码方法，该方法分为三个步骤：（1）在解码层中选择一个成熟层和一个业余层，（2）使用一个与水印相关的问题来确定一个枢轴层，以评估该层是否在视觉上具有良好的 grounding，（3）应用三层对比解码来生成最终输出。在POPE、MME和AMBER等公开基准上的实验表明，我们的方法在减少LVLMs中的幻觉方面达到了最先进的性能，并生成了更具视觉grounding的响应。
英文摘要：
Large Vision-Language Models (LVLMs) have recently shown promising results on various multimodal tasks, even achieving human-comparable performance in certain cases. Nevertheless, LVLMs remain prone to hallucinations -- they often rely heavily on a single modality or memorize training data without properly grounding their outputs. To address this, we propose a training-free, tri-layer contrastive decoding with watermarking, which proceeds in three steps: (1) select a mature layer and an amateur layer among the decoding layers, (2) identify a pivot layer using a watermark-related question to assess whether the layer is visually well-grounded, and (3) apply tri-layer contrastive decoding to generate the final output. Experiments on public benchmarks such as POPE, MME and AMBER demonstrate that our method achieves state-of-the-art performance in reducing hallucinations in LVLMs and generates more visually grounded responses.
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。
