paper-with-me

홈 › Papers

Chain of Images for Intuitively Reasoning

2023-11-09 · Fanxu Meng, Haotong Yang, Yiding Wang, Muhan Zhang

The human brain is naturally equipped to comprehend and interpret visual information rapidly. When confronted with complex problems or concepts, we use flowcharts, sketches, and diagrams to aid our thought process. Leveraging this inherent ability can significantly enhance logical reasoning. However, current Large Language Models (LLMs) do not utilize such visual intuition to help their thinking. Even the most advanced version language models (e.g., GPT-4V and LLaVA) merely align images into textual space, which means their reasoning processes remain purely verbal. To mitigate such limitations, we present a Chain of Images (CoI) approach, which can convert complex language reasoning problems to simple pattern recognition by generating a series of images as intermediate representations. Furthermore, we have developed a CoI evaluation dataset encompassing 15 distinct domains where images can intuitively aid problem-solving. Based on this dataset, we aim to construct a benchmark to assess the capability of future multimodal large-scale models to leverage images for reasoning. In supporting our CoI reasoning, we introduce a symbolic multimodal large language model (SyMLLM) that generates images strictly based on language instructions and accepts both text and image as input. Experiments on Geometry, Chess and Common Sense tasks sourced from the CoI evaluation dataset show that CoI improves performance significantly over the pure-language Chain of Thoughts (CoT) baselines. The code is available at https://github.com/GraphPKU/CoI.

📄 PDF Abstract BibTeX arXiv:2311.09241

Code (1)

graphpku/coi 공식 구현

Tasks

Common Sense ReasoningLanguage ModellingLarge Language ModelLogical ReasoningMultimodal Large Language Model

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning

2025-05-23 · Michael Hassid, Gabriel Synnaeve, Yossi Adi, Roy Schwartz

Reasoning large language models (LLMs) heavily rely on scaling test-time compute to perform complex reasoning tasks by generating extensive "thinking" chains. While demonstrating impressive results, this approach incurs …

Chaining Simultaneous Thoughts for Numerical Reasoning

2022-11-29 · Zhihong Shao, Fei Huang, Minlie Huang

Given that rich information is hidden behind ubiquitous numbers in text, numerical reasoning over text should be an essential skill of AI systems. To derive precise equations to solve numerical reasoning problems, previo…

Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

2019-06-12 · ACL 2019 7 · Yichen Jiang, Nitish Joshi, Yen-Chun Chen, Mohit Bansal

Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpret…

Multi-Hop Reading ComprehensionReading ComprehensionSentence

Interleaved-Modal Chain-of-Thought

2024-11-29 · CVPR 2025 1 · Jun Gao, Yongqi Li, Ziqiang Cao, Wenjie Li

Chain-of-Thought (CoT) prompting elicits large language models (LLMs) to produce a series of intermediate reasoning steps before arriving at the final answer. However, when transitioning to vision-language models (VLMs),…

Guiding Language Model Reasoning with Planning Tokens

2023-10-09 · Xinyi Wang, Lucas Caccia, Oleksiy Ostapenko, Xingdi Yuan 외

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhan…

Language ModelingLanguage ModellingMathmodel