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.
InProceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI), pages 1561–1567
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.