arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.05862cs.LGcs.AIcs.SIstat.ML
收藏

让你的图说话:为LLM编码结构化数据

Let Your Graph Do the Talking: Encoding Structured Data for LLMs

Google Research(谷歌研究院);Waymo Research(Waymo研究院)

Bryan Perozzi, Bahare Fatemi, Dustin Zelle, Anton Tsitsulin, Mehran Kazemi, Rami Al-Rfou, Jonathan Halcrow

AI总结:

提出GraphToken方法,通过参数高效的编码函数将图结构显式编码为提示,供LLM用于多种推理任务,在GraphQA基准上实现最高73个百分点的全面性能提升。

摘要:

我们如何最好地将结构化数据编码为序列形式以供大型语言模型(LLM)使用?在这项工作中,我们引入了一种参数高效的方法来显式地为LLM表示结构化数据。我们的方法GraphToken学习一个编码函数,用显式的结构化信息扩展提示。与专注于有限领域(例如知识图谱表示)的其他工作不同,我们的工作是首个专注于通用编码结构化数据以用于各种推理任务的努力。我们表明,显式表示图结构能够显著改进图推理任务。具体来说,我们看到在GraphQA基准的节点、边和图级任务上全面改进——最高达73个百分点。

英文摘要:

How can we best encode structured data into sequential form for use in large language models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly represent structured data for LLMs. Our method, GraphToken, learns an encoding function to extend prompts with explicit structured information. Unlike other work which focuses on limited domains (e.g. knowledge graph representation), our work is the first effort focused on the general encoding of structured data to be used for various reasoning tasks. We show that explicitly representing the graph structure allows significant improvements to graph reasoning tasks. Specifically, we see across the board improvements - up to 73% points - on node, edge and, graph-level tasks from the GraphQA benchmark.

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。

↑