@article{whatdoesyourshortanswervqascoreactuallym, title = {What Does Your Short-Answer VQA Score Actually Measure? Evaluator-Dependent Instability in Multimodal Short-Answer Benchmarks}, author = {Guanhua Ye and Niu Jingbin and Yan Li and Meiyu Liang and Zhe Xue and Yingxia Shao and Yawen Li}, year = {2026}, eprint = {2607.10240}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.10240}, }