MLLMs show late-layer textual override of correct visual predictions, with a directional signature enabling a simple inference-time recovery method that improves conflict benchmarks by up to 9.4%.
Robust multimodal large lan- guage models against modality conflict.arXiv preprint arXiv:2507.07151,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias
MLLMs show late-layer textual override of correct visual predictions, with a directional signature enabling a simple inference-time recovery method that improves conflict benchmarks by up to 9.4%.