用数列生成代码任务，提升大模型的归纳推理能力
Code-Driven Inductive Synthesis: Enhancing Reasoning Abilities of Large Language Models with Sequences
- 以数列规律为题，通过代码求解生成归纳推理数据
- 在代码和综合推理任务上均显著提升模型表现
- 适合研究模型推理机制或数据构建的新手
大语言模型在推理能力方面取得显著进展，但现有研究多集中于演绎推理（如代码与数学），而更贴近人类学习方式的归纳推理仍缺乏深入研究。主要原因在于高质量过程监督数据难以获取。为此，我们创新性地采用数列作为归纳推理数据源，将数列包装为算法问题，通过代码求解找出数列通项。利用代码单元测试验证解法对任意项的有效性，从而注入基于案例的监督信号。我们构建了序列合成数据流水线，形成训练数据集 CodeSeq。实验表明，使用 CodeSeq 训练的模型在代码和综合推理基准测试中均有提升。
原文摘要 · Abstract (English)
Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive reasoning, is not well studied. We attribute the reason to the fact that obtaining high-quality process supervision data is challenging for inductive reasoning. Towards this end, we novelly employ number sequences as the source of inductive reasoning data. We package sequences into algorithmic problems to find the general term of each sequence through a code solution. In this way, we can verify whether the code solution holds for any term in the current sequence, and inject case-based supervision signals by using code unit tests. We build a sequence synthetic data pipeline and form a training dataset CodeSeq. Experimental results show that the models tuned with CodeSeq improve on both code and comprehensive reasoning benchmarks.
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。