Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding ACL

Kuo Liao | Shuang Li | Meng Zhao | Liqun Liu | Mengge Xue | Zhenyu Hu | Honglin Han | Chengguo Yin |

Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors ACL

Mengge Xue | Zhenyu Hu | Liqun Liu | Kuo Liao | Shuang Li | Honglin Han | Meng Zhao | Chengguo Yin |

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence EMNLP

Junru Lu | Jiazheng Li | Siyu An | Meng Zhao | Yulan He | Di Yin | Xing Sun |