LETHE uses parameter-level model merging plus prompt-level word definitions to dilute backdoor behavior in LLMs, cutting attack success to below 7% in most tested settings.
Recursive deep models for semantic composi- tionality over a sentiment treebank
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution
LETHE uses parameter-level model merging plus prompt-level word definitions to dilute backdoor behavior in LLMs, cutting attack success to below 7% in most tested settings.