Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack. (arXiv:2312.06924v1 [cs.CL]) Show more
http://arxiv.org/abs/2312.06924 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.
