SOURCE-LINKED INTELLIGENCE

Confident but Wrong: A Constrained Decoding Diagnostic for Low-Resource Automatic Post-Editing

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Automatic Post-Editing (APE) for low-resource languages (LRLs) often fails to improve Machine Translation (MT), and the score alone cannot say why: whether more training would help, or whether the training data is too inconsistent to learn from. We introduce a black-box, inference-time diagnostic that tells these two cases apart without retraining or annotation. It varies an edit-distance penalty $λ$ that drives the model from free editing towards copying the MT, and reads two signals: (1) the shape of the Translation Edit Rate (TER)-vs-$λ$ curve, U-shaped if edits from the model reduce error

Read original source ↗ Open in workspace

recordType

paper

region

Global