Papers
arxiv:2407.00468

MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation

Published on Jun 29
· Submitted by leonardPKU on Jul 2
Authors:
,
,
,
,
,
,
,
,
,
,

Abstract

Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, often assessed through multiple-choice questions (MCQs) that include an image, a question, and several options. However, many benchmarks used for such evaluations suffer from systematic biases. Remarkably, Large Language Models (LLMs) without any visual perception capabilities achieve non-trivial performance, undermining the credibility of these evaluations. To address this issue while maintaining the efficiency of MCQ evaluations, we propose MMEvalPro, a benchmark designed to avoid Type-I errors through a trilogy evaluation pipeline and more rigorous metrics. For each original question from existing benchmarks, human annotators augment it by creating one perception question and one knowledge anchor question through a meticulous annotation process. MMEvalPro comprises 2,138 question triplets, totaling 6,414 distinct questions. Two-thirds of these questions are manually labeled by human experts, while the rest are sourced from existing benchmarks (MMMU, ScienceQA, and MathVista). Compared with the existing benchmarks, our experiments with the latest LLMs and LMMs demonstrate that MMEvalPro is more challenging (the best LMM lags behind human performance by 31.73%, compared to an average gap of 8.03% in previous benchmarks) and more trustworthy (the best LLM trails the best LMM by 23.09%, whereas the gap for previous benchmarks is just 14.64%). Our in-depth analysis explains the reason for the large performance gap and justifies the trustworthiness of evaluation, underscoring its significant potential for advancing future research.

Community

Paper author Paper submitter

A more trustworthy and efficient benchmark for LMMs!

Visit our homepage and leaderboard at: https://mmevalpro.github.io/
Huggingface Dataset: https://huggingface.co/datasets/MM-Diagnose/MMEvalPro
Github: https://github.com/chenllliang/MMEvalPro

Fantastic benchmark!

Heartbreaking, but incredibly valuable lessons

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2407.00468 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2407.00468 in a Space README.md to link it from this page.

Collections including this paper 5