聚光与阴影：基于注意力的双锚点反思解码用于MLLM幻觉缓解
Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation
AI总结：
本文提出双锚点反思解码框架DaID，通过动态校准每个token生成来缓解MLLM幻觉，利用视觉注意力分布指导双锚点选择，提升推理能力。
摘要：
多模态大语言模型（MLLMs）展示了卓越的推理能力，但仍面临幻觉问题，即生成文本与视觉内容矛盾。本文引入双锚点反思解码（DaID），一种新的对比解码框架，通过挖掘模型内部感知差异动态校准每个token生成。具体而言，DaID识别出一个聚光层以增强视觉事实信号，一个阴影层以抑制文本惯性。通过利用视觉注意力分布指导此双锚点选择过程，我们的方法确保了精确的token特定适应。在多个基准和MLLMs上的实验结果表明，DaID显著缓解了幻觉问题，同时增强了通用推理能力。
英文摘要：
Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities yet continue to suffer from hallucination, where generated text contradicts visual content. In this paper, we introduce Dual-Anchor Introspective Decoding (DaID), a novel contrastive decoding framework that dynamically calibrates each token generation by mining the model's internal perceptual discrepancies. Specifically, DaID identifies a Spotlight layer to amplify visual factual signals and a Shadow layer to suppress textual inertia. By leveraging visual attention distributions to guide this dual-anchor selection process, our method ensures precise, token-specific adaptation. Experimental results across multiple benchmarks and MLLMs demonstrate that DaID significantly mitigates hallucination while enhancing general reasoning capabilities.
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。
