提升大模型对图结构的理解能力，解决位置偏见问题。
GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding
- 将关键信息置于大模型记忆更强的位置，改善位置偏差。
- 引入轻量外部知识库增强弱记忆区域的表征能力。
- 支持多步推理任务，适用于复杂图分析场景。
尽管大型语言模型（LLMs）在处理图数据方面展现出潜力，但在通过图描述序列理解图结构信息时表现不佳，尤其在图规模增大时更为明显。我们将其归因于大模型在图描述序列中不同位置的记忆性能不均，即“位置偏见”。为此，我们提出GraphInsight框架，旨在提升大模型对图结构宏观与微观信息的理解。该框架基于两个核心策略：1）将关键图信息放置在大模型记忆性能较强的位置；2）借鉴检索增强生成（RAG），为记忆较弱区域引入轻量外部知识库。此外，GraphInsight探索将这两种策略集成到大模型智能体流程中，以应对需要多步推理的复合图任务。在涵盖多种评估任务的基准上进行的大量实证研究显示，GraphInsight显著优于所有其他图描述方法（如提示技术、重排序策略），在不同规模的图结构理解任务中表现优异。
原文摘要 · Abstract (English)
Although Large Language Models (LLMs) have demonstrated potential in processing graphs, they struggle with comprehending graphical structure information through prompts of graph description sequences, especially as the graph size increases. We attribute this challenge to the uneven memory performance of LLMs across different positions in graph description sequences, known as ''positional biases''. To address this, we propose GraphInsight, a novel framework aimed at improving LLMs' comprehension of both macro- and micro-level graphical information. GraphInsight is grounded in two key strategies: 1) placing critical graphical information in positions where LLMs exhibit stronger memory performance, and 2) investigating a lightweight external knowledge base for regions with weaker memory performance, inspired by retrieval-augmented generation (RAG). Moreover, GraphInsight explores integrating these two strategies into LLM agent processes for composite graph tasks that require multi-step reasoning. Extensive empirical studies on benchmarks with a wide range of evaluation tasks show that GraphInsight significantly outperforms all other graph description methods (e.g., prompting techniques and reordering strategies) in understanding graph structures of varying sizes.
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。