MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs
Keywords: Multimodal LLM; Instruction Following; Benchmark
TL;DR: We introduce MIA-Bench, a benchmark designed to assess MLLMs’ ability to strictly adhere to complex instructions.
Abstract: Effective evaluation of Multimodal Large Language Models (MLLMs) is essential for understanding their capabilities and limitations. In this paper, we introduce MIA-Bench, a benchmark designed to assess MLLMs’ ability to strictly adhere to complex instructions. Our benchmark comprises a diverse set of 400 image-prompt pairs, each crafted to challenge the models’ compliance with layered instructions in generating accurate and contextually appropriate responses. Evaluation results from a wide array of state-of-the-art MLLMs reveal significant variations in performance, highlighting areas for improvement in instruction fidelity. Additionally, we create extra training data and explore supervised fine-tuning and direct preference optimization to enhance the models’ ability to strictly follow instructions without compromising performance on other tasks. We hope this benchmark not only serves as a tool for measuring MLLM adherence to instructions, but also guides future developments in MLLM training methods.
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.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
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: 7815
Loading