ACL Findings2026
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
Raman Saparkhan, Majd Hawasly, Md. Rizwan Parvez, Mohammad Raza
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- STaR: Bootstrapping Reasoning With Reasoning cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- STaR: Bootstrapping Reasoning With Reasoning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- PAL: Program-aided Language Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- PAL: Program-aided Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving cites STaR: Bootstrapping Reasoning With Reasoning
- ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving cites PAL: Program-aided Language Models
- ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds on14
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- STaR: Bootstrapping Reasoning With ReasoningEric Zelikman, Yuhuai Wu, Jesse Mu, Noah D. GoodmanNeurIPS 2022 · 1,126 citations
- PAL: Program-aided Language ModelsLuyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon et al.ICML 2023 · 700 citations
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
- ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem SolvingZhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen et al.ICLR 2024 · 289 citations
Related papers
- Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step ReasoningYiwei Li, Peiwen Yuan, Shaoxiong Feng, Boyuan Pan et al.ICLR 2024 · 101 citations
- Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All ScenariosLei Lin, Jia-Yi Fu, Pengli Liu, Qingyang Li et al.ACL Findings 2024 · 3 citations
- Self-Training Elicits Concise Reasoning in Large Language ModelsTergel Munkhbat, Namgyu Ho, Seo Hyun Kim, Yongjin Yang et al.ACL Findings 2025 · 3 citations
- Optimal Self-Consistency for Efficient Reasoning with Large Language ModelsAustin Feng, Marius Alonso, Ambroise Odonnat, Vasilii Feofanov et al.ICML 2026 · 6 citations
- Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMsPranjal Aggarwal, Aman Madaan, Yiming Yang, MausamEMNLP 2023 · 5 citations
