paper-with-me

홈 › Papers

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

2026-04-19 · Raman Saparkhan, Majd Hawasly, Md Rizwan Parvez, Mohammad Raza arxiv

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 9.3x. 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.

📄 PDF Abstract BibTeX arXiv:2604.17433

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PEDAL: Enhancing Greedy Decoding with Large Language Models using Diverse Exemplars

2024-08-16 · Sumanth Prabhu

Self-ensembling techniques with diverse reasoning paths such as Self-Consistency have demonstrated remarkable performance gains in text generation with Large Language Models (LLMs). However, such techniques depend on the…

ARCDiversityText Generation

Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model

2020-05-15 · Quande Liu, Lequan Yu, Luyang Luo, Qi Dou 외

Training deep neural networks usually requires a large amount of labeled data to obtain good performance. However, in medical image analysis, obtaining high-quality labels for the data is laborious and expensive, as accu…

ClassificationGeneral Classificationimage-classificationImage Classification+5

The Impact of LLM Self-Consistency and Reasoning Effort on Automated Scoring Accuracy and Cost

2026-04-03 · Scott Frohn arxiv

Strategic model selection and reasoning settings are more effective than ensembling for optimizing automated scoring with large language models (LLMs). We examined self-consistency (intra-model majority voting) and reaso…

High School Mathematics

ACAR: Adaptive Complexity Routing for Multi-Model Ensembles with Auditable Decision Traces

2026-02-06 · Ramchand Kumaresan arxiv

We present ACAR (Adaptive Complexity and Attribution Routing), a measurement framework for studying multi-model orchestration under auditable conditions. ACAR uses self-consistency variance (sigma) computed from N=3 prob…

Self-Consistency Improves Chain of Thought Reasoning in Language Models

2022-03-21 · Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le 외

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the …

ARCArithmetic ReasoningGSM8KLanguage Modelling+2