MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs. Spurious bias, a tendency to use spurious correlations between non-essential input attributes and target variables for predictions, has revealed a severe robustness pitfall in deep learning models trained on single modality data.
Jun 24, 2024
Jun 24, 2024 · We introduce MM-SpuBench, a comprehensive visual question-answering (VQA) benchmark designed to evaluate MLLMs' reliance on nine distinct categories of ...
Jun 24, 2024 · A comprehensive visual question-answering (VQA) benchmark designed to evaluate MLLMs' reliance on nine distinct categories of spurious correlations from five ...
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs ... What is the Visual Cognition Gap between Humans and Multimodal LLMs? X ...
Spurious bias, a tendency to use spurious correlations between non-essential input attributes and target variables for predictions, has revealed a severe ...
To better understand this problem, we introduce MM-SpuBench, a comprehensive visual question-answering (VQA) benchmark designed to evaluate MLLMs' reliance on ...
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs ... Benchmarking Spurious Bias in Few-Shot Image Classifiers. G Zheng, W Ye ...
This paper provides a comprehensive overview of jailbreaking research targeting both LLMs and MLLMs, highlighting recent advancements in evaluation benchmarks, ...
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs ... to train an image classifier to be robust to spurious correlations.
Jun 24, 2024 · 论文旨在分析多模态大语言模型(MLLMs)中的虚假偏差,并提出一种综合视觉和语言模型的视觉问答基准测试集MM-SpuBench,以评估当前MLLMs对于五个开源图像数据 ...