Pith. sign in

REVIEW 1 cited by

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.12934 v1 pith:XFNGOAXY submitted 2024-10-16 cs.CL

classification cs.CL
keywords llmsreasoningstepcoanswerbest-of-nconsumptioncorrectiongenerate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems. However, this repeated independent process often leads to the same mistakes, making the selected solution still incorrect. We propose a novel prompting method named Stepwise Correction (StepCo) that helps LLMs identify and revise incorrect steps in their generated reasoning paths. It iterates verification and revision phases that employ a process-supervised verifier. The verify-then-revise process not only improves answer correctness but also reduces token consumption with fewer paths needed to generate. With StepCo, a series of LLMs demonstrate exceptional performance. Notably, using GPT-4o as the backend LLM, StepCo achieves an average accuracy of 94.1 across eight datasets, significantly outperforming the state-of-the-art Best-of-N method by +2.4, while reducing token consumption by 77.8%.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment

    cs.AI 2025-02 conditional novelty 6.0 of 10

    RaLU aligns natural-language reasoning with program logic by decomposing generated code into control-flow units and self-correcting each one, reporting modest accuracy gains on math and code benchmarks.

Pith tools