通过基于图的合成数据增强大型语言模型的逻辑推理能力
Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data
AI总结：
本研究探索基于图的合成数据作为训练信号，通过监督微调增强LLM在归纳与空间推理任务上的能力，且不影响其他基准表现。
摘要：
尽管近期在大型语言模型（LLM）的训练和提示策略方面取得了进展，这些模型在处理涉及长推理链的复杂逻辑推理任务时仍面临挑战。在本工作中，我们探索了使用基于图的合成推理数据作为训练信号来增强LLM推理能力的潜力和局限性。我们在两个已建立的自然语言推理任务——归纳推理和空间推理——上进行了广泛实验，结果表明，使用基于图的合成推理数据进行监督微调（SFT）能有效提升LLM的推理性能，同时不损害其在其他标准评估基准上的表现。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
