Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models

TL;DR

The paper introduces Image-of-Thought prompting, a novel method enabling multimodal large language models to extract and refine visual rationales step-by-step, significantly enhancing zero-shot visual reasoning and interpretability.

Contribution

It proposes the IoT prompting technique that automatically designs visual information extraction steps, integrating visual and textual rationales for improved multimodal reasoning.

Findings

Improved zero-shot visual reasoning performance across tasks

Enhanced interpretability through step-by-step visual explanations

Effective in various multimodal large language models

Abstract

Recent advancements in Chain-of-Thought (CoT) and related rationale-based works have significantly improved the performance of Large Language Models (LLMs) in complex reasoning tasks. With the evolution of Multimodal Large Language Models (MLLMs), enhancing their capability to tackle complex multimodal reasoning problems is a crucial frontier. However, incorporating multimodal rationales in CoT has yet to be thoroughly investigated. We propose the Image-of-Thought (IoT) prompting method, which helps MLLMs to extract visual rationales step-by-step. Specifically, IoT prompting can automatically design critical visual information extraction operations based on the input images and questions. Each step of visual information refinement identifies specific visual rationales that support answers to complex visual reasoning questions. Beyond the textual CoT, IoT simultaneously utilizes visual and textual rationales to help MLLMs understand complex multimodal information. IoT prompting has improved zero-shot visual reasoning performance across various visual understanding tasks in different MLLMs. Moreover, the step-by-step visual feature explanations generated by IoT prompting elucidate the visual reasoning process, aiding in analyzing the cognitive processes of large multimodal models