CompassDPO: Dynamics-Controlled Direct Preference Optimization for Robust Safety Alignment

arXiv:2603.07211v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes training sensitive to imperfect supervision. Existing robust DPO methods often address this sensitivity through global loss corrections or external data-level interventions, while largely overlooking how unreliable comparisons distort batch-level optimization dynamics. We propose CompassDPO, a reward-free DPO framework that stabilizes preference optimization through dynamics control. Using the implic

Source: arXiv cs.LG — read the full report at the original publisher.

This is a curated wire item. The Continuum Brief does not republish full third-party articles; this entry links to the original source.