Short-term group fairness in repeated selections can incur a high price of fairness even with nearly identical group distributions, but long-term disparities can vanish under simple investment policies with low PoF.
Constrained policy optimization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
PREFINE adapts Direct Preference Optimization to trajectory-level preferences in RL for joint reward retention and safety alignment in continuous domains.
Proposes a probabilistic framework for latent agentic substructures in DNNs using log-score utilities and log pooling, with proofs on unanimity and an application to persona emergence in LLM alignment.
citing papers explorer
-
Price of Fairness in Short-Term and Long-Term Algorithmic Selections
Short-term group fairness in repeated selections can incur a high price of fairness even with nearly identical group distributions, but long-term disparities can vanish under simple investment policies with low PoF.
-
PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment
PREFINE adapts Direct Preference Optimization to trajectory-level preferences in RL for joint reward retention and safety alignment in continuous domains.
-
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
Proposes a probabilistic framework for latent agentic substructures in DNNs using log-score utilities and log pooling, with proofs on unanimity and an application to persona emergence in LLM alignment.