SOURCE-LINKED INTELLIGENCE

StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine Translation

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Machine translation systems are periodically upgraded to stronger models, but the available preference signal is human post-edits of an older system's outputs, which the newer model may already surpass. Moreover, collecting fresh post-edits for every new model is prohibitively expensive. We call this the Stale Preference problem. Standard DPO can fail in this setting: it may increase the likelihood of inferior post-edits, erode the model's existing quality, and fail to provide the per-token control needed to correct localized errors. We introduce StalePO, an objective derived from three requir

Read original source ↗ Open in workspace

recordType

paper

region

Global