paper-with-me

Papers

WorldVQA: Measuring Atomic World Knowledge in Multimodal Large Language Models

2026-01-28 · Runjie Zhou, Youbo Shao, Haoyu Lu, Bowei Xing, Tongtong Bai, Yujie Chen, Jie Zhao, Lin Sui, Haotian Yao, Zijia Zhao, Hao Yang, Haoning Wu, Zaida Zhou, Jinguo Zhu, Zhiqi Huang, Yiping Bao, Yangyang Liu, Y. Charles, Xinyu Zhou arxiv

We introduce WorldVQA, a benchmark designed to evaluate the atomic visual world knowledge of Multimodal Large Language Models (MLLMs). Unlike current evaluations, which often conflate visual knowledge retrieval with reasoning, WorldVQA decouples these capabilities to strictly measure "what the model memorizes." The benchmark assesses the atomic capability of grounding and naming visual entities across a stratified taxonomy, spanning from common head-class objects to long-tail rarities. We expect WorldVQA to serve as a rigorous test for visual factuality, thereby establishing a standard for assessing the encyclopedic breadth and hallucination rates of current and next-generation frontier models.

📄 PDF Abstract BibTeX arXiv:2602.02537

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models

2026-07-27 · Zichao Lin, Yifeng Xie, Bowen Qu, Haiming Wang 외 hf

We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Models (MLLMs). Existing benchmarks often fail to isolate perception: hol…

What do Models Learn From Training on More Than Text? Measuring Visual Commonsense Knowledge

2022-05-14 · ACL 2022 5 · Lovisa Hagström, Richard Johansson

There are limitations in learning language from text alone. Therefore, recent focus has been on developing multimodal models. However, few benchmarks exist that can measure what language models learn about language from …

Exploring Failure Cases in Multimodal Reasoning About Physical Dynamics

2024-02-24 · Sadaf Ghaffari, Nikhil Krishnaswamy

In this paper, we present an exploration of LLMs' abilities to problem solve with physical reasoning in situated environments. We construct a simple simulated environment and demonstrate examples of where, in a zero-shot…

Language ModelingLanguage ModellingMultimodal ReasoningObject+1

What do models learn from training on more than text? Measuring visual commonsense knowledge

2022-01-16 · ACL ARR January 2022 1 · Anonymous

There are limitations in learning language from text alone. Therefore, recent focus has been on developing multimodal models. However, few benchmarks exist that can measure what language models learn about language from …

6 Fingers, 1 Kidney: Natural Adversarial Medical Images Reveal Critical Weaknesses of Vision-Language Models

2025-12-03 · Leon Mayer, Piotr Kalinowski, Caroline Ebersbach, Marcel Knopp 외 arxiv

Vision-language models (VLMs) are increasingly integrated into clinical workflows. However, existing benchmarks primarily assess performance on common anatomical presentations and fail to capture the challenges posed by …