Login / Signup

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models.

Sarah BallFrauke KreuterNina Rimsky
Published in: CoRR (2024)
Keyphrases
  • language model
  • probabilistic model
  • retrieval model
  • n gram
  • language modeling
  • information retrieval
  • latent variables
  • feature vectors
  • query expansion
  • mixture model
  • document retrieval