Conditional Attribute Transformers jointly estimate next-token probabilities and conditional attribute values for autoregressive sequence models, enabling credit assignment, counterfactuals, and steerable generation in one pass.
Blei, and Victor Veitch
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Develops an adversary-free counterfactual prediction framework by deriving a variational objective that upper-bounds mutual information between stochastic representations and treatments.
citing papers explorer
-
Conditional Attribute Estimation with Autoregressive Sequence Models
Conditional Attribute Transformers jointly estimate next-token probabilities and conditional attribute values for autoregressive sequence models, enabling credit assignment, counterfactuals, and steerable generation in one pass.
-
Adversary-Free Counterfactual Prediction via Information-Regularized Representations
Develops an adversary-free counterfactual prediction framework by deriving a variational objective that upper-bounds mutual information between stochastic representations and treatments.