Mechanistic analysis of GLMs shows graph sink tokens have high activation but low importance for predictions, indicating decoupling between saliency and graph-semantic utility.
Quantifying explanation quality in graph neural networks using out-of-distribution generalization.arXiv preprint arXiv:2602.07708, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.