pith. sign in

Learning to reason faithfully through step-level faithful- ness maximization.arXiv preprint arXiv:2602.03507, 2026a

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

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning

cs.AI · 2026-06-02 · unverdicted · novelty 6.0

ThoughtFold applies introspective redundancy detection within correct CoT trajectories to create sub-trajectory spectra, then uses masked preference optimization to penalize redundant explorations, yielding 56% token reduction on DeepSeek-R1-Distill-Qwen-7B while preserving accuracy.

citing papers explorer

Showing 1 of 1 citing paper.

  • ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning cs.AI · 2026-06-02 · unverdicted · none · ref 10

    ThoughtFold applies introspective redundancy detection within correct CoT trajectories to create sub-trajectory spectra, then uses masked preference optimization to penalize redundant explorations, yielding 56% token reduction on DeepSeek-R1-Distill-Qwen-7B while preserving accuracy.