A multimodal scene graph with contrastive learning, injected as a decoder soft prompt, gives small ChartQA gains, but ablations show the visual graph alone often matches or beats it.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph-Based Multimodal Contrastive Learning for Chart Question Answering
A multimodal scene graph with contrastive learning, injected as a decoder soft prompt, gives small ChartQA gains, but ablations show the visual graph alone often matches or beats it.