测试多模态大模型在相同内容下的跨模态不一致问题
Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs
- 设计新基准测试，评估图像、文本、混合模态下模型一致性
- 15个主流模型表现差异大，即使文字识别正确仍不一致
- 视觉特征如颜色、分辨率影响结果，适合关注多模态对齐的研究者
我们提出两个新基准REST和REST+（渲染等价性压力测试），用于系统评估多模态大语言模型（MLLMs）的跨模态不一致问题。尽管MLLMs将视觉与语言映射到同一嵌入空间，却无法在不同模态间执行相同任务。这些基准包含三模态（图像、文本、混合）语义相同的样本，结果显示当前最先进的MLLMs无法在不同模态间保持一致推理。我们评估了15个MLLMs，发现模态不一致程度差异显著，即便排除文字识别（OCR）问题也依然存在。无论将文字转为图像或图像转为文字，都无法解决不一致问题。即使OCR正确，视觉特征（如文字颜色、分辨率，但非字体）以及视觉令牌数量仍会影响模型表现。最后，我们的一致性评分与文本与图像间的模态差距相关，揭示了跨模态不一致的机制根源。
原文摘要 · Abstract (English)
We introduce two new benchmarks REST and REST+ (Render-Equivalence Stress Tests) to enable systematic evaluation of cross-modal inconsistency in multimodal large language models (MLLMs). MLLMs are trained to represent vision and language in the same embedding space, yet they cannot perform the same tasks in both modalities. Our benchmarks contain samples with the same semantic information in three modalities (image, text, mixed) and we show that state-of-the-art MLLMs cannot consistently reason over these different modalities. We evaluate 15 MLLMs and find that the degree of modality inconsistency varies substantially, even when accounting for problems with text recognition (OCR). Neither rendering text as image nor rendering an image as text solves the inconsistency. Even if OCR is correct, we find that visual characteristics (text colour and resolution, but not font) and the number of vision tokens have an impact on model performance. Finally, we find that our consistency score correlates with the modality gap between text and images, highlighting a mechanistic interpretation of cross-modal inconsistent MLLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。