Faithful reasoning and safety pull in opposite directions in current reasoning models, and the two behaviors are controlled by anti-correlated internal vectors that can be steered independently.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Risky Business: Measuring The Faithfulness-Safety Tension
Faithful reasoning and safety pull in opposite directions in current reasoning models, and the two behaviors are controlled by anti-correlated internal vectors that can be steered independently.