Login / Signup

Hijacking Large Language Models via Adversarial In-Context Learning.

Yao QiangXiangyu ZhouDongxiao Zhu
Published in: CoRR (2023)
Keyphrases
  • language model
  • n gram
  • information retrieval
  • language modeling
  • probabilistic model
  • context sensitive
  • machine learning
  • language model for information retrieval
  • bayesian networks
  • test collection
  • retrieval model