Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis.
Kai ChenChunwei WangKuo YangJianhua HanLanqing HongFei MiHang XuZhengying LiuWenyong HuangZhenguo LiDit-Yan YeungLifeng ShangXin JiangQun LiuPublished in: CoRR (2023)