Pixelated Instructions: Can Multimodal Large Language Models Follow Printed Instructions in Images?

Xiujun Li, Yujie Lu, Zhe Gan, Jianfeng Gao, William Yang Wang, Yejin Choi

Keywords: multimodal large langauage models, instruction following

TL;DR: This paper explores the instruction following capabilities of multimodal LLMs in the Pixelated Instructions setting, identify a common issue for the existing multimodal LLMs, and also provide a v-MLLM model for solution.

Abstract: Recent multimodal large language models (MLLMs) have shown promising instruction following capabilities on vision-language tasks. In this work, we introduce VISUAL MODALITY INSTRUCTION (VIM), and investigate how well multimodal models can understand textual instructions provided in pixels, despite not being explicitly trained on such data during pretraining or fine-tuning. We adapt VIM to eight benchmarks, including OKVQA, MM-Vet, MathVista, MMMU, and probe diverse MLLMs in both the text-modality instruction (TEM) setting and VIM setting. Notably, we observe a significant performance disparity between the original TEM and VIM settings for open-source MLLMs, indicating that open-source MLLMs face greater challenges when text instruction is presented solely in image form. To address this issue, we train V-MLLM, a generalizable model that is capable to conduct robust instruction following in both text-modality and visual-modality instructions.

Primary Area: datasets and benchmarks

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5353