English

Multimodal Chain-of-Thought Reasoning in Language Models

Computation and Language 2024-05-21 v5 Artificial Intelligence Computer Vision and Pattern Recognition

Abstract

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 have primarily focused on the language modality. We propose Multimodal-CoT that incorporates language (text) and vision (images) modalities into a two-stage framework that separates rationale generation and answer inference. In this way, answer inference can leverage better generated rationales that are based on multimodal information. Experimental results on ScienceQA and A-OKVQA benchmark datasets show the effectiveness of our proposed approach. With Multimodal-CoT, our model under 1 billion parameters achieves state-of-the-art performance on the ScienceQA benchmark. Our analysis indicates that Multimodal-CoT offers the advantages of mitigating hallucination and enhancing convergence speed. Code is publicly available at https://github.com/amazon-science/mm-cot.

Keywords

Cite

@article{arxiv.2302.00923,
  title  = {Multimodal Chain-of-Thought Reasoning in Language Models},
  author = {Zhuosheng Zhang and Aston Zhang and Mu Li and Hai Zhao and George Karypis and Alex Smola},
  journal= {arXiv preprint arXiv:2302.00923},
  year   = {2024}
}

Comments

Published in Transactions on Machine Learning Research

R2 v1 2026-06-28T08:29:58.386Z