paper-with-me

홈 › Papers

Multimodal Chain-of-Thought Reasoning in Language Models

2023-02-02 · Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, Alex Smola

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.

📄 PDF Abstract BibTeX arXiv:2302.00923

Code (3)

amazon-science/mm-cot 공식 구현 pytorch
chengtan9907/mc-cot pytorch
xqx12/daily-info pytorch

Tasks

HallucinationLanguage ModellingScience Question Answering

Similar Papers 제목 키워드 기반

Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models

2025-08-18 · Tan-Hanh Pham, Chris Ngo arxiv

Many reasoning techniques for large multimodal models adapt language model approaches, such as Chain-of-Thought (CoT) prompting, which express reasoning as word sequences. While effective for text, these methods are subo…

Multimodal Reasoning

Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models

2023-05-26 · Yao Yao, Zuchao Li, Hai Zhao

With the widespread use of language models (LMs) in NLP tasks, researchers have discovered the potential of Chain-of-thought (CoT) to assist LMs in accomplishing complex reasoning tasks by generating intermediate steps. …

GSM8KMultimodal ReasoningRepresentation Learning

CheXthought: A global multimodal dataset of clinical chain-of-thought reasoning and visual attention for chest X-ray interpretation

2026-04-29 · Sonali Sharma, Jin Long, George Shih, Sarah Eid 외 arxiv

Chest X-ray interpretation is one of the most frequently performed diagnostic tasks in medicine and a primary target for AI development, yet current vision-language models are primarily trained on datasets of paired imag…

Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings

2023-05-03 · Daniel Rose, Vaishnavi Himakunthala, Andy Ouyang, Ryan He 외

Recent advances in large language models elicit reasoning in a chain-of-thought that allows models to decompose problems in a human-like fashion. Though this paradigm improves multi-step reasoning ability in language mod…

Data AugmentationQuestion AnsweringVisual Storytelling

VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use

2025-05-25 · Mingyuan Wu, Jingcheng Yang, Jize Jiang, Meitang Li 외

Reinforcement Learning Finetuning (RFT) has significantly advanced the reasoning capabilities of large language models (LLMs) by enabling long chains of thought, self-correction, and effective tool use. While recent work…

Multimodal ReasoningQuestion AnsweringVisual Question AnsweringVisual Reasoning