DuPO: Enabling Reliable Self-Verification via Dual Preference Optimization
Shuaijie She · Yu Bao · Yu Lu · Lu Xu · Tao Li · Wenhao Zhu · Jianbing Zhang · Shujian Huang · Shanbo Cheng · Lu Lu · Yuxuan Wang
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Shuaijie She · Yu Bao · Yu Lu · Lu Xu · Tao Li · Wenhao Zhu · Jianbing Zhang · Shujian Huang · Shanbo Cheng · Lu Lu · Yuxuan Wang
Botian Wang · Yawen Ouyang · Yaohui Li · Mianzhi Pan · yuanhang tang · Haorui Cui · Yiqun Wang · Jianbing Zhang · Xiaonan Wang · Wei-Ying Ma · Hao Zhou
Shanbo Cheng · Shuaijie She · Yu Bao · Jianbing Zhang · Jiajun Chen · Shujian Huang
Large language models (LLMs) with long context windows offer the potential to translate entire documents in a single pass, yet they frequently suffer from catastrophic information distortion, undermining the strict faithfulness required for translation. This challenge is compounded by the scarcit...
Mianzhi Pan · Jianfei Li · Peishuo Liu · Botian Wang · Yawen Ouyang · Yiming Rong · Wei-Ying Ma · Hao Zhou · Jianbing Zhang