Reasoning models often determine refusal of harmful requests early in the chain-of-thought, with the opening sentence in distilled models fully controlling the outcome and patterns transferring across models from the same teacher.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Where Do Reasoning Models Refuse?
Reasoning models often determine refusal of harmful requests early in the chain-of-thought, with the opening sentence in distilled models fully controlling the outcome and patterns transferring across models from the same teacher.