E Computational resources The main experiments is conducted on 8 NVIDIA 6000 ada gpus for around 200 hours

Similar preprints — Semantic Scholar

Cited by (1)

• ReflCtrl: Controlling LLM Reflection via Representation Engineering

  ReflCtrl demonstrates that self-reflection in reasoning LLMs is governed by an identifiable direction in latent representation space and that suppressing this direction via stepwise steering can reduc