作者位次 #3/8ACL 2026Poster· Natural Language Processing
Automatic and Reliable Evaluation for Academic Caption-to-Figure Generation with LMM s
Guanghui Ye · Huan Zhao · Qin Zhu · Fengnan Li · Jiaqi Li · Yixian Shen · Zhonghao Ren · Zhihua Jiang
摘要
Existing datasets for evaluating text-to-image generation focus mostly on real-life images, which poses challenges for assessing academicfigure generation given real scientific captions, which is a hot topic in AI for Science. To fill the gap, we propose HE4AFG, a novel datasetwhich first provide...