Login / Signup

Detecting Pretraining Data from Large Language Models.

Weijia ShiAnirudh AjithMengzhou XiaYangsibo HuangDaogao LiuTerra BlevinsDanqi ChenLuke Zettlemoyer
Published in: CoRR (2023)
Keyphrases
  • language model
  • probabilistic model
  • language modeling
  • training data
  • n gram
  • co occurrence
  • machine translation