AP-MAE reconstructs masked attention patterns in LLMs with high accuracy, generalizes across models, predicts generation correctness at 55-70%, and enables 13.6% accuracy gains via targeted interventions.
In this section we include the plots of all average SHAP values for each task and model
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
-
Automated Attention Pattern Discovery at Scale in Large Language Models
AP-MAE reconstructs masked attention patterns in LLMs with high accuracy, generalizes across models, predicts generation correctness at 55-70%, and enables 13.6% accuracy gains via targeted interventions.