用两个样本实现高精度推理，显著降低大模型计算成本。
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
- 融合思维链与程序链两种推理模式，构建混合集成方法
- 仅需2个样本即可达成78.6%任务的准确推理，采样量减少9.3倍
- 适合追求高效推理且资源受限的应用场景
自一致性（SC）是一种通过聚合多个采样输出来提升大语言模型推理准确率的常用技术，但其高昂的计算成本源于大量采样。本文提出一种混合集成方法，结合思维链（CoT）和程序链（PoT）两种推理模式的优势。我们设计了一个通用框架，用于在自一致性中融合这两种推理形式，并提出了完整的采样与早停策略。实验表明，CoT-PoT集成不仅提升了整体准确率，还将实现自一致性所需的样本数量减少了9.3倍。特别地，在78.6%的任务中，仅需两个样本即可完成有效推理，这一效果在以往任何自一致性方法中均未实现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。