The paper introduces Frictive Policy Optimization as a risk-sensitive epistemic control framework for LLM alignment that treats interventions like clarification, verification, and refusal as explicit actions to improve downstream belief quality rather than immediate rewards.
Artificial Intelligence, 112(1–2):181–211
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignment
The paper introduces Frictive Policy Optimization as a risk-sensitive epistemic control framework for LLM alignment that treats interventions like clarification, verification, and refusal as explicit actions to improve downstream belief quality rather than immediate rewards.