Pith. sign in

REVIEW 1 cited by

Self-Consistency Boosts Calibration for Math Reasoning

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 2403.09849 v1 pith:NDOZ6LRG submitted 2024-03-14 cs.CL cs.AI

Self-Consistency Boosts Calibration for Math Reasoning

classification cs.CL cs.AI
keywords calibrationmethodsaccuracyconfidencekadavathmathmodelreasoning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development. We design three off-the-shelf calibration methods based on self-consistency (Wang et al., 2022) for math reasoning tasks. Evaluation on two popular benchmarks (GSM8K and MathQA) using strong open-source LLMs (Mistral and LLaMA2), our methods better bridge model confidence and accuracy than existing methods based on p(True) (Kadavath et al., 2022) or logit (Kadavath et al., 2022).

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

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

  1. Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty

    cs.AI 2026-06 unverdicted novelty 7.0

    Structural uncertainty from self-preference-induced rankings of LLM reasoning paths complements answer dispersion for identifying unreliable instances on logical tasks while collapsing on factual retrieval.