LIRA aligns latent instruction representations in LLMs to defend against jailbreaks, backdoors, and undesired knowledge, blocking over 99% of PEZ attacks and achieving optimal WMDP forgetting.
Gemini 2.0 flash, 2024
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.LG 1years
2026 1verdicts
UNVERDICTED 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs
LIRA aligns latent instruction representations in LLMs to defend against jailbreaks, backdoors, and undesired knowledge, blocking over 99% of PEZ attacks and achieving optimal WMDP forgetting.