collaborators

1 paper

cs.AI2026

CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning

Rabimba Karanjai, Qun Gu, Hemanth Hegadehalli Madhavarao +8

Direct Preference Optimization (DPO) treats all constraint violations equally: a 1,000 overshoot induce the same training signal. It is also susceptible…