Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation
Zhang, Yuhui, Su, Yuchang, Liu, Yiming, Wang, Xiaohan, Burgess, James, Sui, Elaine, Wang, Chenyu, Aklilu, Josiah, Lozano, Alejandro, Wei, Anjiang, Schmidt, Ludwig, Yeung-Levy, Serena
–arXiv.org Artificial Intelligence
The rapid development of vision language models (VLMs) demands rigorous and reliable evaluation. However, current visual question answering (VQA) benchmarks often depend on open-ended questions, making accurate evaluation difficult due to the variability in natural language responses. To address this, we introduce AutoConverter, an agentic framework that automatically converts these open-ended questions into multiple-choice format, enabling objective evaluation while reducing the costly question creation process. Our experiments demonstrate that AutoConverter can generate correct and challenging multiple-choice questions, with VLMs demonstrating consistently similar or lower accuracy on these questions compared to human-created ones. Using AutoConverter, we construct VMCBench, a benchmark created by transforming 20 existing VQA datasets into a unified multiple-choice format, totaling 9,018 questions. We comprehensively evaluate 33 state-of-the-art VLMs on VMCBench, setting a new standard for scalable, consistent, and reproducible VLM evaluation.
arXiv.org Artificial Intelligence
Jan-6-2025
- Country:
- Asia > India (1.00)
- North America > United States (0.92)
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Education (1.00)
- Leisure & Entertainment (0.92)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.96)
- Natural Language
- Chatbot (1.00)
- Large Language Model (1.00)
- Representation & Reasoning > Agents (0.68)
- Vision (1.00)
- Machine Learning > Neural Networks
- Information Technology > Artificial Intelligence