Stochastic Attention adds calibrated uncertainty to transformer foundation models through inference-time multinomial sampling of attention weights and univariate post-hoc tuning of a concentration parameter.
Contextual dropout: An efficient sample-dependent dropout module
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention
Stochastic Attention adds calibrated uncertainty to transformer foundation models through inference-time multinomial sampling of attention weights and univariate post-hoc tuning of a concentration parameter.