Open access
2026
Beyond VQA Accuracy: A Cross-Regime Diagnostic Evaluation of Symbol Consistency in Multimodal Large Language Models
A cross-regime diagnostic framework for evaluating symbol consistency in MLLMs is proposed and its multi-stage failure mechanisms are revealed, offering a reusable diagnostic perspective for reliability assessment and symbol-capability improvement in MLLMs.
Chuanche Wang, Ruifeng Guo, Pengfei Xiu et al.
· IEEE Access · 0 citations