Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Corrupting CoT
anchor
Findings
IC-458
Most VLM decoders show negative CC-SHAP on VALSE multiple-choice, indicating their explanations are less self-consistent than their answers, driven by a shift from text-dominant to image-dominant processing
[compared-to]
IC-458
Most VLM decoders show negative CC-SHAP on VALSE multiple-choice, indicating their explanations are less self-consistent than their answers, driven by a shift from text-dominant to image-dominant processing
[supporting]