#artificial intelligence
Sep 2025
GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts
GSM8K-V is introduced, a benchmark transforming GSM8K into multi-image sequences with semantic equivalence preserved and error analysis shows that the primary bottleneck lies in Implicit Visual Inference Error (IVIE), where models fail to recover visual semantics that are implied rather than explicitly stated.
Fan Yuan, Yuchen Yan, Yi-Fan Jiang et al.
· arXiv.org · 8 citations