作者位次 #2/7ACL 2026Poster· Natural Language Processing
Beyond Ranking: Fine-Grained Diagnostics and Self-Improvement for MLLM s
Mingze Xu · Zijing Zhao · Qiming Peng · Houwen Peng · Han Hu · Zhanhui Kang · Yuxing Han
摘要
While Multimodal Large Language Models (MLLMs) are advancing rapidly, accurately evaluating their capabilities remains challenging. Current paradigms primarily rely on holistic scoring and static leaderboards, which fail to disentangle fine-grained competencies. Specifically, they suffer from “Ou...