InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training 文章

ArXiv CS.CL2026-06-01NEWSen作者: Pengkai Wang, Pengwei Liu, Qi Zuo, Zhijie Sang, Congkai Xie, Hongxia Yang

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training · 相关人物

暂无数据