StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine Translation
StalePO is introduced, an objective derived from three requirements this regime imposes that improves the fraction of segments passing all LLM-as-judge MQM quality checks by 14.9 and 4.6 percentage points, respectively, with gains concentrated on style and fluency.
Rohit Dhaipule, Sukhdeep Singh Kharbanda, Prasanth Bathala et al.
· 0 citations