pith. sign in

entire week

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Decoding the Critique Mechanism in Large Reasoning Models

cs.LG · 2026-03-17 · unverdicted · novelty 6.0

By injecting arithmetic mistakes into CoT reasoning, the paper identifies a hidden critique ability in LRMs and extracts a steerable critique vector that enhances self-correction across model scales.

citing papers explorer

Showing 1 of 1 citing paper.

  • Decoding the Critique Mechanism in Large Reasoning Models cs.LG · 2026-03-17 · unverdicted · none · ref 16

    By injecting arithmetic mistakes into CoT reasoning, the paper identifies a hidden critique ability in LRMs and extracts a steerable critique vector that enhances self-correction across model scales.