Uncategorized

Universal Vulnerabilities in Large Language Models: In-context Learning Backdoor Attacks. (arXiv:2401.05949v1 [cs.CL])



"Large Language Models"In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *