Diagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation

Excerpt

arXiv:2609.22793v1 Announce Type: new Abstract: LLM-based machine translation evaluation can closely match human judgments, but in practice it remains largely diagnostic, with the signals rarely translating into direct quality improvements under real production constraints. We propose a two-stage, evaluator-guided automatic post-editing framework that turns MQM-style evaluation into targeted repairs: a retrieval-augmented LLM evaluator outputs structured, span-level MQM diagnoses under an explic