视觉思维链：多模态填充填补逻辑间隙（英文版）

英文标题：Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings中文摘要：通过视觉增强实现 VCoT 方法，利用多模态填充降低序列数据中的逻辑间隙，改善下游任务的表现及对模型的多步推理提供可解释性。在视觉叙事和 WikiHow 摘要数据集上，VCoT 方法通过人类评估超越了思维链基线模型，提供了新的、一致的合成数据增强。英文摘要：Recent advances in large language models elicit reasoning in a chain ofthought that allows models to decompose problems in a human-like fashion.Though this paradigm improves multi-step reasoning ability in language models,it is limited by being unimodal and applied mainly to question-an