让大模型学会自动执行算法，通过分解式训练提升推理能力。
Large Language Models and Algorithm Execution: Application to an Arithmetic Function
- 用分解式监督训练引导模型理解算法步骤
- 在算术函数任务上显著提升复杂推理能力
- 适合需要精准逻辑推演的研究与工程场景
大型语言模型（LLMs）近期展现出新的高级功能，其有效性依赖于统计学习和泛化能力。然而，它们在内化处理数据方面存在局限，难以自主执行算法。本文研究通过专注的分解式监督训练，扩展模型执行算法的能力。我们提出 LLM-DAL（Large Language Model - Decompositional Algorithmic Learning）训练框架，证明当训练方法合理设计以引导学习过程时，大模型在执行复杂算法推理和泛化方面的能力可得到显著提升。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have recently developed new advanced functionalities. Their effectiveness relies on statistical learning and generalization capabilities. However, they face limitations in internalizing the data they process and struggle, for instance, to autonomously execute algorithms. In this paper, we investigate the possibility of extending these models' capabilities to algorithm execution through specialized supervised training focused on reasoning decomposition. We introduce a training model called LLM-DAL (Large Language Model - Decompositional Algorithmic Learning), through which we demonstrate that LLMs' ability to perform complex algorithmic inferences and generalize can be significantly improved when the training method is properly designed to guide the model in its learning process.
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。