English

What Makes Multimodal In-Context Learning Work?

Computer Vision and Pattern Recognition 2024-04-26 v2 Artificial Intelligence

Abstract

Large Language Models have demonstrated remarkable performance across various tasks, exhibiting the capacity to swiftly acquire new skills, such as through In-Context Learning (ICL) with minimal demonstration examples. In this work, we present a comprehensive framework for investigating Multimodal ICL (M-ICL) in the context of Large Multimodal Models. We consider the best open-source multimodal models (e.g., IDEFICS, OpenFlamingo) and a wide range of multimodal tasks. Our study unveils several noteworthy findings: (1) M-ICL primarily relies on text-driven mechanisms, showing little to no influence from the image modality. (2) When used with advanced-ICL strategy (like RICES), M-ICL is not better than a simple strategy based on majority voting over context examples. Moreover, we identify several biases and limitations of M-ICL that warrant consideration prior to deployment. Code available at https://gitlab.com/folbaeni/multimodal-icl

Keywords

Cite

@article{arxiv.2404.15736,
  title  = {What Makes Multimodal In-Context Learning Work?},
  author = {Folco Bertini Baldassini and Mustafa Shukor and Matthieu Cord and Laure Soulier and Benjamin Piwowarski},
  journal= {arXiv preprint arXiv:2404.15736},
  year   = {2024}
}

Comments

20 pages, 16 figures. Accepted to CVPR 2024 Workshop on Prompting in Vision. Project page: https://folbaeni.gitlab.io/multimodal-icl

R2 v1 2026-06-28T16:04:51.919Z