Login / Signup

Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning.

Mustafa Safa ÖzdayiCharith PerisJack FitzGeraldChristophe DupuyJimit MajmudarHaidar KhanRahil ParikhRahul Gupta
Published in: CoRR (2023)
Keyphrases
  • language model
  • training data
  • language modeling
  • knowledge discovery
  • probabilistic model
  • information retrieval
  • n gram
  • xml documents