SIRAS: Sibling-Relative Advantage Shaping for Reinforcement Learning from Verifiable Rewards
Zairun Yang · Jun Xu · Lei Liang · Huajun Chen · Qiang Zhang
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。
Zairun Yang · Jun Xu · Lei Liang · Huajun Chen · Qiang Zhang
Yichi Zhang · Zhuo Chen · Lingbing Guo · Jun Xu · Mengshu Sun · Zhizhen Liu · Lei Liang · Wen Zhang · Huajun Chen
Question answering (QA) with reference texts is a classic application scenario for large language models (LLMs), where high standards for the credibility and traceability of generated answers are crucial. Many existing approaches focus on generating multi-level citations linked to specific refere...
Jun Xu · Xinkai Du · Yu Ao · Peilong Zhao · Yang Li · Ling Zhong · Lin Yuan · Zhongpu Bo · Xiaorui Wang · Mengshu Sun · Zhengke Gui · Dalong Zhang · ZhaoYang Wang · Qiwei Wang · Yangyang Hou · ZhiYing Yi · Haofen Wang · Huajun Chen · Lei Liang · Jun Zhou