作者位次 #4/6ACL 2026Findings· Findings of ACL
E du MARS : Can Vision-Language Models Grade Like Teachers? Benchmarking Multimodal, Rubric-Based Assessment on C hinese K -12 Answers
Xuan Zhao · Jiashun Chen · Wanting xu · Huiyuan Yan · Chaowei Fang · Xing Wei
摘要
Automated grading of student work is a critical application of AI in education. However, existing benchmarks fall short in evaluating models on realistic, cognitively demanding tasks. Most rely on synthetic, well-structured text inputs, overlooking the multimodal, error-prone, and often handwritt...