Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
S. Si, H. Zhao, C. Gao, Yuntao Bai, Zhengtao Wang, B. Gao, K. Luo, Wentao Li, Y. Huang, Guanduo Chen, F. Qi, Mingchuan Zhang, B. Chang, Maosong Sun