Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking

Abstract

Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching, reward-driven updates modify the transport trajectories but lack inherent constraints to pretrained data manifold, often pushing generated (terminal) samples off the pretrained support. We formalize this failure mode as ``manifold drift``, a phenomenon where preference-aligned trajectories diverge from the pretrained support. Theoretically, we prove that while optimal flow matching exactly preserves the terminal manifold, existing methods like FlowDPO fail to do so whenever reward-driven updates contain components normal to the manifold surface. As a remedy, we propose **ThermoDPO**, a temperature-controlled objective that anchors pairwise preference optimization on preferred samples. Across temperature regimes, this objective connects rejection sampling fine-tuning and FlowDPO while upper-bounding a reconstruction-based surrogate for manifold drift. To counteract diminished signals at low temperatures, we further introduce a weighted variant, **ThermoDPO-weighted**, which we evaluate across all experiments for its superior trade-off between preference alignment and manifold preservation. Empirically, **ThermoDPO-weighted** demonstrates a better trade-off on synthetic manifolds than FlowDPO variants. On real-world image benchmarks, it improves OCR-oriented alignment over the pretrained model and FlowDPO variants while remaining competitive with strong baselines in held-out model-based and human evaluations without visible sample degradation.