Login / Signup
DistillSeq: A Framework for Safety Alignment Testing in Large Language Models using Knowledge Distillation.
Mingke Yang
Yuqi Chen
Yi Liu
Ling Shi
Published in:
CoRR (2024)
Keyphrases
</>
language model
probabilistic model
speech recognition
language modeling
context sensitive
n gram
document retrieval
test collection
ad hoc information retrieval
knowledge discovery
retrieval model
speech signal
relevance model
statistical language models