Login / Signup

BadEdit: Backdooring large language models by model editing.

Yanzhou LiTianlin LiKangjie ChenJian ZhangShangqing LiuWenhan WangTianwei ZhangYang Liu
Published in: CoRR (2024)
Keyphrases
  • language model
  • probabilistic model
  • speech recognition
  • statistical model
  • language modeling
  • bayesian networks
  • test collection
  • retrieval model
  • context sensitive
  • translation model