SEAM measures VLM reasoning consistency across modalities using paired semantically equivalent textual and visual notations, and finds systematic vision-language imbalance.
Gpt-4o mini: Advancing cost-efficient intelligence, 2024 b
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
SEAM measures VLM reasoning consistency across modalities using paired semantically equivalent textual and visual notations, and finds systematic vision-language imbalance.