Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Does Refusal Training in LLMs Generalize to the Past Tense?
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-322
Past-tense reformulations of harmful requests bypass refusal training in eight released LLMs, while future-tense reformulations are substantially less effective
IC-323
O1-mini and O1-preview reasoning models are vulnerable to past-tense reformulations (84% and 78% ASR) but produce less specific jailbroken outputs than non-reasoning models