Search papers, labs, and topics across Lattice.
Frictive Policy Optimization (FPO) is introduced as a framework for training LLMs to explicitly manage epistemic and normative risks through strategic interventions like clarification and refusal. FPO formalizes alignment as a risk-sensitive epistemic control problem, optimizing for downstream epistemic quality rather than immediate reward. The paper presents a taxonomy of interventions, a structured friction functional, and a family of FPO methods, along with an evaluation framework focused on epistemic competence.
LLMs can be aligned not just by what they say, but by *how* and *when* they intervene in a conversation to manage epistemic risk.
We propose Frictive Policy Optimization (FPO), a framework for learning language model policies that regulate not only what to say, but when and how to intervene in order to manage epistemic and normative risk. Unlike standard alignment methods that optimize surface-level preference or task utility, FPO treats clarification, verification, challenge, redirection, and refusal as explicit control actions whose purpose is to shape the evolution of belief, commitment, and uncertainty over time. We formalize alignment as a risk-sensitive epistemic control problem in which intervention decisions are selected based on their expected effect on downstream epistemic quality rather than on immediate reward alone. We introduce a compact taxonomy of frictive interventions, a structured friction functional that operationalizes multiple alignment failure modes, and a unified family of FPO methods spanning reward shaping, preference pairing, group-relative ranking, and risk-conditioned trust regions. We further propose an evaluation framework that measures epistemic competence directly through clarification behavior, calibration, contradiction repair, refusal proportionality, and information efficiency. Together, these results provide a formal and algorithmic foundation for learning agents that are aligned not only in outcome, but in epistemic conduct.
