MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation.
Yihang Wang, Bowen Tian, Yueyang Su, Yixing Fan, Jiafeng Guo
Browse the full COLING paper archive.
Yihang Wang, Bowen Tian, Yueyang Su, Yixing Fan, Jiafeng Guo
Browse the full COLING paper archive.