用自动生成的逻辑题训练大模型，显著提升推理能力。
Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus
- 基于符号逻辑设计高质量合成样本，构建多样化的推理数据集
- 在逻辑、数学和编码任务上最高提升30分，整体推理能力显著增强
- 适合想提升模型逻辑推理能力的研究者与开发者使用
大型语言模型虽能应对多种任务，但在推理方面仍表现不佳。为此，我们提出一种名为附加逻辑训练（ALT）的方法，通过程序生成的逻辑推理样本来增强模型的推理能力。首先，结合符号逻辑理论与已有实证经验，确立高质量样本的设计原则；随后，依据这些原则构建了一个名为形式化逻辑推理由多样化（FLD×2）的合成语料库，包含多步推导、未知事实、多样化推理规则、多样化语言表达及具有挑战性的干扰项。实验表明，在FLD×2上进行的ALT可显著提升当前先进大模型（如LLaMA-3.1-70B）的推理能力，逻辑推理基准测试最高提升30分，数学与编程基准最高提升10分，BBH基准套件提升5分。
原文摘要 · Abstract (English)
Large language models (LLMs) are capable of solving a wide range of tasks, yet they have struggled with reasoning. To address this, we propose $\textbf{Additional Logic Training (ALT)}$, which aims to enhance LLMs' reasoning capabilities by program-generated logical reasoning samples. We first establish principles for designing high-quality samples by integrating symbolic logic theory and previous empirical insights. Then, based on these principles, we construct a synthetic corpus named $\textbf{Formal Logic Deduction Diverse}$ ($\textbf{FLD}$$_{\times 2}$), comprising numerous samples of multi-step deduction with unknown facts, diverse reasoning rules, diverse linguistic expressions, and challenging distractors. Finally, we empirically show that ALT on FLD$_{\times2}$ substantially enhances the reasoning capabilities of state-of-the-art LLMs, including LLaMA-3.1-70B. Improvements include gains of up to 30 points on logical reasoning benchmarks, up to 10 points on math and coding benchmarks, and 5 points on the benchmark suite BBH.
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。