Enhancing Reasoning Skills in Small Persian Medical Language Models Can Outperform Large-Scale Data Training
增强小规模波斯语医疗语言模型的推理能力可超越大规模数据训练
机构 * Faculty of Computer Engineering University of Isfahan(计算机工程系 布鲁金斯大学) ; School of Computer Science University of Windsor(计算机科学学院 温莎大学)
专题命中 推理评测 :reasoning(title,abstract);chain-of-thought(abstract);CoT(abstract);分类 cs.CL
AI总结 通过RLAIF和DPO方法,提升小规模波斯语医疗模型推理能力,使其在有限数据下超越大规模训练模型。
Comments 7 pages, 5 figures