GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design
This addresses the problem of evaluating and enhancing LLMs for graph learning tasks without training, offering a baseline for researchers, though it is incremental as it builds on existing prompt engineering methods.
The authors tackled the lack of a comprehensive benchmark for evaluating large language models (LLMs) on graph-structured data through prompt design alone, and introduced GraphICL, a benchmark with structured prompts that enabled general-purpose LLMs to outperform specialized graph models in resource-constrained and out-of-domain tasks.
The growing importance of textual and relational systems has driven interest in enhancing large language models (LLMs) for graph-structured data, particularly Text-Attributed Graphs (TAGs), where samples are represented by textual descriptions interconnected by edges. While research has largely focused on developing specialized graph LLMs through task-specific instruction tuning, a comprehensive benchmark for evaluating LLMs solely through prompt design remains surprisingly absent. Without such a carefully crafted evaluation benchmark, most if not all, tailored graph LLMs are compared against general LLMs using simplistic queries (e.g., zero-shot reasoning with LLaMA), which can potentially camouflage many advantages as well as unexpected predicaments of them. To achieve more general evaluations and unveil the true potential of LLMs for graph tasks, we introduce Graph In-context Learning (GraphICL) Benchmark, a comprehensive benchmark comprising novel prompt templates designed to capture graph structure and handle limited label knowledge. Our systematic evaluation shows that general-purpose LLMs equipped with our GraphICL outperform state-of-the-art specialized graph LLMs and graph neural network models in resource-constrained settings and out-of-domain tasks. These findings highlight the significant potential of prompt engineering to enhance LLM performance on graph learning tasks without training and offer a strong baseline for advancing research in graph LLMs.