用图结构合成数据提升大模型的复杂逻辑推理能力。
Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data
- 构建图结构的合成推理数据用于训练
- 在归纳与空间推理任务上显著提升表现
- 保持原有基准任务性能，适合推理增强
尽管大语言模型在训练和提示策略上取得进展，但在涉及长推理链的复杂逻辑任务中仍存在挑战。本文探索了基于图结构的合成推理数据作为训练信号，以增强大模型的推理能力。在两个经典自然语言推理任务——归纳推理与空间推理上开展的广泛实验表明，使用合成图结构推理数据进行监督微调（SFT），可有效提升大模型的推理性能，且不损害其在其他标准评估基准上的表现。
原文摘要 · Abstract (English)
Despite recent advances in training and prompting strategies for Large Language Models (LLMs), these models continue to face challenges with complex logical reasoning tasks that involve long reasoning chains. In this work, we explore the potential and limitations of using graph-based synthetic reasoning data as training signals to enhance LLMs' reasoning capabilities. Our extensive experiments, conducted on two established natural language reasoning tasks -- inductive reasoning and spatial reasoning -- demonstrate that supervised fine-tuning (SFT) with synthetic graph-based reasoning data effectively enhances LLMs' reasoning performance without compromising their effectiveness on other standard evaluation 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。