Pith. sign in

REVIEW 5 cited by

Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2401.10480 v1 pith:FAZDTENS submitted 2024-01-19 cs.CL cs.AI

Yiwei Li , Peiwen Yuan , Shaoxiong Feng , Boyuan Pan , Xinglin Wang , Bin Sun , Heda Wang , Kan Li This is my paper · ORCID
classification cs.CLcs.AI
keywords reasoningsamplingtaskstextbfchain-of-thoughtcostmodelsmulti-step
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Self-consistency (SC) has been a widely used decoding strategy for chain-of-thought reasoning. Despite bringing significant performance improvements across a variety of multi-step reasoning tasks, it is a high-cost method that requires multiple sampling with the preset size. In this paper, we propose a simple and scalable sampling process, \textbf{E}arly-Stopping \textbf{S}elf-\textbf{C}onsistency (ESC), to greatly reduce the cost of SC without sacrificing performance. On this basis, one control scheme for ESC is further derivated to dynamically choose the performance-cost balance for different tasks and models. To demonstrate ESC's effectiveness, we conducted extensive experiments on three popular categories of reasoning tasks: arithmetic, commonsense and symbolic reasoning over language models with varying scales. The empirical results show that ESC reduces the average number of sampling of chain-of-thought reasoning by a significant margin on six benchmarks, including MATH (-33.8%), GSM8K (-80.1%), StrategyQA (-76.8%), CommonsenseQA (-78.5%), Coin Flip (-84.2%) and Last Letters (-67.4%), while attaining comparable performances.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning

    cs.CL 2025-05 conditional novelty 7.0 of 10

    A checkpoint-based search and candidate augmentation method improves small LLM mathematical reasoning accuracy over existing test-time scaling baselines.

  2. Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    DDC reduces token consumption by over 10x in LLM reasoning while maintaining or exceeding baseline accuracy across five benchmarks via adaptive path quality filtering.

  3. Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    TTSP samples and filters multiple zoom-in exploration traces and iteratively consolidates validated observations into an Evidence Ledger, improving fine-grained multimodal reasoning on V* Bench, HR-Bench, TreeBench, a...

  4. Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers

    stat.ML 2026-02 conditional novelty 6.0 of 10

    Tracking only the counts of the two most frequent LLM answers is asymptotically as sample-efficient as the full Bayesian posterior in an adaptive self-consistency procedure, cutting LLM calls by up to half.

  5. Structured Thoughts For Improved Reasoning And Context Pruning

    cs.CL 2026-07 conditional novelty 5.5 of 10

    Structured try/outcome SFT improves math reasoning by up to 8% over standard SFT and enables pruning ~85% of context with ~9% accuracy drop.

Pith tools