Lighter, yet More Faithful: Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization. (arXiv:2311.09335v1 [cs.CL]) Show more
http://arxiv.org/abs/2311.09335 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.