vix.ing · top · new · best · stats

M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought

2024/05/26 by Qiguang Chen, Chen, Qiguang, Libo Qin +9 · 65 citations
Computer Science · Physics and Astronomy · #Advanced Text Analysis Techniques #Artificial Intelligence (cs.AI) #Complex Network Analysis Techniques #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2405.16473

openalex publication_date 2024/05/26 · openalex created_date 2024/05/29 · openalex updated_date 2026/07/28

Abstract

Multi-modal Chain-of-Thought (MCoT) requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning, which gains increasing attention. Nevertheless, the current MCoT benchmark still faces some challenges: (1) absence of visual modal reasoning, (2) single-step visual modal reasoning, and (3) Domain missing, thereby hindering the development of MCoT. Motivated by this, we introduce a novel benchmark (M3CoT) to address the above challenges, advancing the multi-domain, multi-step, and multi-modal CoT. Additionally, we conduct a thorough evaluation involving abundant MCoT approaches on Vision Large Language Models (VLLMs). In addition, we highlight that the current VLLMs still struggle to correctly reason in M3CoT and there remains a large gap between existing VLLMs and human performance in M3CoT, despite their superior results on previous MCoT benchmarks. To our knowledge, we take the first meaningful step toward the multi-domain, multi-step, and multi-modal scenario in MCoT. We hope that M3CoT can serve as a valuable resource, providing a pioneering foundation in multi-domain, multi-step, multi-modal chain-of-thought research.

Cited by

Related