小模型也能学会图任务，无需专门编码器。
Less is More: Learning Graph Tasks with Just LLMs
- 用思维链指令训练小模型直接处理图数据。
- 模型在未见图结构和任务上仍能有效泛化。
- 无需图神经网络，纯语言模型即可胜任。
大语言模型（LLMs）在图推理方面具有潜力，可解决多种问题。以往工作尝试通过最佳文本序列化图或结合图神经网络（GNNs）与LLMs来提升图推理能力，但这些方法的实际收益尚不明确。本文通过实证回答三个关键问题：（1）LLMs能否在不依赖专用图编码模型的情况下学习解决基础图任务？（2）它们能否将已学解法泛化到未见的图结构或任务？（3）不同学习图任务的方法有何优劣？结果表明，即使小型LLMs，仅通过包含思维链（chain-of-thought）的指令进行训练，也能有效掌握图任务，且该训练无需专门图编码器，即可在新图结构和新任务上实现良好泛化。
原文摘要 · Abstract (English)
For large language models (LLMs), reasoning over graphs could help solve many problems. Prior work has tried to improve LLM graph reasoning by examining how best to serialize graphs as text and by combining GNNs and LLMs. However, the merits of such approaches remain unclear, so we empirically answer the following research questions: (1) Can LLMs learn to solve fundamental graph tasks without specialized graph encoding models?, (2) Can LLMs generalize learned solutions to unseen graph structures or tasks?, and (3) What are the merits of competing approaches to learn graph tasks? We show that even small LLMs can learn to solve graph tasks by training them with instructive chain-of-thought solutions, and this training generalizes, without specialized graph encoders, to new tasks and graph structures.
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。