Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model. (arXiv:2310.09520v4 [cs.CL] UPDATED) Show more
http://arxiv.org/abs/2310.09520 #arXiv #NLProc
CleverLibre Social is an inclusive social instance for open discussion, learning, and community. All cultures welcome. Hate speech and harassment strictly forbidden.