APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training.
Jun Rao, Zepeng Lin, Xuebo Liu, Xiaopeng Ke, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang
Browse the full ACL paper archive.
Jun Rao, Zepeng Lin, Xuebo Liu, Xiaopeng Ke, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang
Browse the full ACL paper archive.