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.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
In a coordination game with switching costs and logit quantal response, endogenous hard transformations (action deletion) eliminate inertia better than soft ones (taxes), while meta-level antagonistic social preferences can block individually Pareto-improving reforms.
Multi-agent free-energy minimization under bounded rationality and local information yields approximate Nash equilibria, with cooperative games represented variationally as Gibbs distributions over coalitions and a free-energy version of the Harsanyi dividend for synergy.
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.
-
Why Efficient Reforms Fail: Endogenous Game Transformation under Status Quo Bias and Social Preferences
In a coordination game with switching costs and logit quantal response, endogenous hard transformations (action deletion) eliminate inertia better than soft ones (taxes), while meta-level antagonistic social preferences can block individually Pareto-improving reforms.
-
A Collective Variational Principle Unifying Bayesian Inference, Game Theory, and Thermodynamics
Multi-agent free-energy minimization under bounded rationality and local information yields approximate Nash equilibria, with cooperative games represented variationally as Gibbs distributions over coalitions and a free-energy version of the Harsanyi dividend for synergy.