Skip to main navigation Skip to search Skip to main content

Self-Consistency from Only Two Samples: CoT–PoT Ensembling for Efficient LLM Reasoning

  • Carnegie Mellon University in Qatar
  • Hamad bin Khalifa University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to extensive sampling. We introduce a hybrid ensembling approach that leverages the complementary strengths of two distinct modes of reasoning: Chain-of-Thought (CoT) and Program-of-Thought (PoT). We describe a general framework for combining these two forms of reasoning in self-consistency, as well as particular strategies for both full sampling and early-stopping. We show that CoT-PoT ensembling not only improves overall accuracy, but also drastically reduces the number of samples required for SC by a factor of 9.3×. In particular, the majority of tasks (78.6%) can be addressed with only two samples, which has not been possible with any prior SC methods.

Original languageEnglish
Title of host publication64th Annual Meeting of the Association for Computational Linguistics, Findings of the Association for Computational Linguistics
Subtitle of host publicationACL 2026
EditorsMaria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
PublisherAssociation for Computational Linguistics (ACL)
Pages32804-32839
Number of pages36
ISBN (Electronic)9798891763951
Publication statusPublished - 2026
Event64th Annual Meeting of the Association for Computational Linguistics, ACL 2026 - San Diego, United States
Duration: 2 Jul 2026 → 7 Jul 2026

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference64th Annual Meeting of the Association for Computational Linguistics, ACL 2026
Country/TerritoryUnited States
CitySan Diego
Period2/07/26 → 7/07/26

Fingerprint

Dive into the research topics of 'Self-Consistency from Only Two Samples: CoT–PoT Ensembling for Efficient LLM Reasoning'. Together they form a unique fingerprint.

Cite this