Large language models (LLMs) have shown impressive performance on complex reasoning by leveraging chain-of-thought (CoT) prompting to generate intermediate reasoning chains as the rationale to infer the answer. However, existing CoT studies are mostly isolated in the language modality with LLMs, where LLMs are hard to deploy. To elicit CoT reasoning in multimodality, a possible solution is to fine-tune small language models by fusing the vision and language features to perform CoT reasoning. The key challenge is that those language models tend to generate hallucinated reasoning chains that mislead the answer inference. To mitigate the effect of such mistakes, we propose Multimodal-CoT that incorporates vision features. The framework separates the rationale generation and answer inference into two stages. By incorporating the vision features in both stages, the model is able to generate effective rationales that contribute to answer inference. With Multimodal-CoT, our model under 1 billion parameters outperforms the previous state-of-the-art LLM (GPT-3.5) by 16% (75.17%->91.68%) on the ScienceQA benchmark and even surpasses human performance. Code is publicly available at https://github.com/amazon-science/mm-cot.

翻译：大型语言模型（LLMs）通过利用思维链（CoT）提示生成中间推理链作为推断答案的依据，在复杂推理任务上展现出令人瞩目的能力。然而，现有的CoT研究大多局限于LLMs的语言模态，而LLMs本身难以部署。为在多模态场景中激发CoT推理，一种可行方案是通过融合视觉与语言特征对小型语言模型进行微调，使其能够执行CoT推理。关键挑战在于，这些语言模型容易生成误导答案推理的幻觉式推理链。为缓解此类错误的影响，我们提出融合视觉特征的Multimodal-CoT框架。该框架将推理链生成与答案推理分为两个阶段。通过在两个阶段中融入视觉特征，模型能够生成有助于答案推理的有效推理链。采用Multimodal-CoT后，我们的参数量不足10亿的模型在ScienceQA基准测试中比此前最优的LLM（GPT-3.5）提升16%（从75.17%提升至91.68%），甚至超越人类表现。代码已开源：https://github.com/amazon-science/mm-cot。