ByDeWay：以无训练方式通过深度提示增强你的多模态LLM
ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way
AI总结：
ByDeWay是一个无训练框架，通过分层深度提示（LDP）策略将场景按深度分层并生成区域描述，为多模态大语言模型提供空间上下文，从而在不修改参数的情况下显著提升空间推理能力并减少幻觉。
摘要：
我们介绍了ByDeWay，这是一个旨在增强多模态大语言模型（MLLMs）性能的无训练框架。ByDeWay采用了一种名为分层深度提示（LDP）的新颖提示策略，该策略在不修改任何模型参数的情况下改善了空间推理和定位。它使用单目深度估计将场景分割为最近层、中距层和最远层，然后利用一个定位视觉语言模型生成特定区域的描述。这些结构化、深度感知的描述被附加到图像-问题提示中，为其丰富了空间上下文。这引导MLLMs产生更加有据可依且减少幻觉的回答。我们的方法轻量、模块化，并且兼容黑盒MLLMs。在幻觉敏感（POPE）和推理密集（GQA）基准上的实验表明，在多个MLLMs上均有一致的提升，验证了零训练设置下深度感知提示的有效性。
英文摘要：
We introduce ByDeWay, a training-free framework designed to enhance the performance of Multimodal Large Language Models (MLLMs). ByDeWay uses a novel prompting strategy called Layered-Depth-Based Prompting (LDP), which improves spatial reasoning and grounding without modifying any model parameters. It segments the scene into closest, mid-range, and farthest layers using monocular depth estimation, then generates region-specific captions with a grounded vision-language model. These structured, depth-aware captions are appended to the image-question prompt, enriching it with spatial context. This guides MLLMs to produce more grounded and less hallucinated responses. Our method is lightweight, modular, and compatible with black-box MLLMs. Experiments on hallucination-sensitive (POPE) and reasoning-intensive (GQA) benchmarks show consistent improvements across multiple MLLMs, validating the effectiveness of depth-aware prompting in a zero-training setting.
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。
