arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.20330cs.CV
收藏

我们评估大型视觉-语言模型的方式是否正确?

Are We on the Right Way for Evaluating Large Vision-Language Models?

University of Science and Technology of China(中国科学技术大学);The Chinese University of Hong Kong(香港中文大学);Shanghai AI Laboratory(上海人工智能实验室)

Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, Feng Zhao

AI总结:

针对LVLM评测中视觉冗余与数据泄漏问题,本文提出含1,500个精选样本的MMStar基准及两项评测指标,并系统评估16个主流模型。

摘要:

大型视觉-语言模型(LVLMs)近来取得了快速进展,引发了大量评估其多模态能力的研究。然而,我们深入考察当前评估工作后发现两个主要问题:1)许多样本并不需要视觉内容。答案可以直接从问题和选项,或LLM中嵌入的世界知识推断出来。这一现象在当前基准测试中普遍存在。例如,GeminiPro在没有任何视觉输入的情况下在MMMU基准上达到42.9%,并在六个基准上平均超过随机选择基线24%以上。2)LLM和LVLM训练中存在非故意的数据泄漏。LLM和LVLM在没有视觉内容的情况下仍能回答一些必须依赖视觉的问题,这表明它们在大规模训练数据中记住了这些样本。例如,Sphinx-X-MoE在无法访问图像的情况下在MMMU上获得43.6%,超过其LLM骨干17.9%。这两个问题都会导致对实际多模态增益的误判,并可能误导LVLM研究。为此,我们提出MMStar,这是一个由人工精心挑选的1,500个样本组成的精英级、视觉不可或缺的多模态基准。MMStar对6项核心能力和18个详细维度进行基准测试,旨在通过经过仔细平衡和净化的样本来评估LVLM的多模态能力。这些样本首先通过自动化流水线从当前基准中粗选,然后引入人工审核,以确保每个精选样本都表现出视觉依赖性、最小的数据泄漏,并需要高级多模态能力。此外,我们开发了两个指标来衡量多模态训练中的数据泄漏和实际性能增益。我们在MMStar上评估了16个领先的LVLM以评估其多模态能力,并使用所提出的指标在7个基准上调查它们的数据泄漏和实际多模态增益。

英文摘要:

Large vision-language models (LVLMs) have recently achieved rapid progress, sparking numerous studies to evaluate their multi-modal capabilities. However, we dig into current evaluation works and identify two primary issues: 1) Visual content is unnecessary for many samples. The answers can be directly inferred from the questions and options, or the world knowledge embedded in LLMs. This phenomenon is prevalent across current benchmarks. For instance, GeminiPro achieves 42.9% on the MMMU benchmark without any visual input, and outperforms the random choice baseline across six benchmarks over 24% on average. 2) Unintentional data leakage exists in LLM and LVLM training. LLM and LVLM could still answer some visual-necessary questions without visual content, indicating the memorizing of these samples within large-scale training data. For example, Sphinx-X-MoE gets 43.6% on MMMU without accessing images, surpassing its LLM backbone with 17.9%. Both problems lead to misjudgments of actual multi-modal gains and potentially misguide the study of LVLM. To this end, we present MMStar, an elite vision-indispensable multi-modal benchmark comprising 1,500 samples meticulously selected by humans. MMStar benchmarks 6 core capabilities and 18 detailed axes, aiming to evaluate LVLMs' multi-modal capacities with carefully balanced and purified samples. These samples are first roughly selected from current benchmarks with an automated pipeline, human review is then involved to ensure each curated sample exhibits visual dependency, minimal data leakage, and requires advanced multi-modal capabilities. Moreover, two metrics are developed to measure data leakage and actual performance gain in multi-modal training. We evaluate 16 leading LVLMs on MMStar to assess their multi-modal capabilities, and on 7 benchmarks with the proposed metrics to investigate their data leakage and actual multi-modal gain.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑