Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Yuanfu, Ma, Zhengnan, Fang, Yi, Ma, Jing, Tan, Qiaoyu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2501.15755
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915123428327424
author Sun, Yuanfu
Ma, Zhengnan
Fang, Yi
Ma, Jing
Tan, Qiaoyu
author_facet Sun, Yuanfu
Ma, Zhengnan
Fang, Yi
Ma, Jing
Tan, Qiaoyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15755
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design
Sun, Yuanfu
Ma, Zhengnan
Fang, Yi
Ma, Jing
Tan, Qiaoyu
Machine Learning
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.
title GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design
topic Machine Learning
url https://arxiv.org/abs/2501.15755