no code implementations • 4 Feb 2024 • Jiaming Ji, Boyuan Chen, Hantao Lou, Donghai Hong, Borong Zhang, Xuehai Pan, Juntao Dai, Yaodong Yang
Here we introduce Aligner, a new efficient alignment paradigm that bypasses the whole RLHF process by learning the correctional residuals between the aligned and the unaligned answers.