Mechanistic analysis of GLMs shows graph sink tokens have high activation but low importance for predictions, indicating decoupling between saliency and graph-semantic utility.
Rethinking explainability in the era of multimodal ai
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Introduces Synergistic Faithfulness metric based on Shapley Interaction Index to evaluate cross-modal synergy in VLM explainers, revealing over-reliance on visual salience in existing methods.
A systematic review of 55 papers finds explainability for multimodal attention-based models is dominated by attention-weight visualizations, while evaluation remains mostly qualitative and non-standardized.
citing papers explorer
-
When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models
Mechanistic analysis of GLMs shows graph sink tokens have high activation but low importance for predictions, indicating decoupling between saliency and graph-semantic utility.
-
Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability
Introduces Synergistic Faithfulness metric based on Shapley Interaction Index to evaluate cross-modal synergy in VLM explainers, revealing over-reliance on visual salience in existing methods.
-
Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models
A systematic review of 55 papers finds explainability for multimodal attention-based models is dominated by attention-weight visualizations, while evaluation remains mostly qualitative and non-standardized.