GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding
This addresses a domain-specific problem for researchers and practitioners using LLMs for graph analysis, offering incremental improvements in graph structure understanding.
The paper tackles the problem of Large Language Models (LLMs) struggling to comprehend graph structures due to positional biases in graph description sequences, and proposes GraphInsight, a framework that improves LLM comprehension by optimizing information placement and using a lightweight external knowledge base, resulting in significant outperformance over other methods on benchmarks with varying graph sizes.
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.