pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Demystifying Long Chain-of-Thought Reasoning in LLMs

cs.CL · 2025-02-05 · unverdicted · novelty 4.0

Experiments show that long CoT reasoning in LLMs emerges with more training compute when reward shaping is used properly, and scaling verifiable rewards from noisy data helps especially on out-of-distribution tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Demystifying Long Chain-of-Thought Reasoning in LLMs cs.CL · 2025-02-05 · unverdicted · none · ref 12

    Experiments show that long CoT reasoning in LLMs emerges with more training compute when reward shaping is used properly, and scaling verifiable rewards from noisy data helps especially on out-of-distribution tasks.