Tag
This paper proposes a three-stream detector that combines residual-stream motion with coarse regions and fine directions to better identify reasoning errors in LLMs, improving selection accuracy by up to 12% over state-of-the-art displacement-only methods.
Proposes Manifold-Guided Attention Steering (MAGS), a trajectory-aware inference-time intervention that corrects reasoning errors in LLMs by projecting attention outputs back to a learned correctness manifold when deviation exceeds a threshold, outperforming static steering methods across math, code, and molecular benchmarks.