Saved in:
Bibliographic Details
Main Authors: Li, Xin, Chen, Weize, Chu, Qizhi, Li, Haopeng, Sun, Zhaojun, Li, Ran, Qian, Chen, Wei, Yiwei, Liu, Zhiyuan, Shi, Chuan, Sun, Maosong, Yang, Cheng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.19667
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914131517374464
author Li, Xin
Chen, Weize
Chu, Qizhi
Li, Haopeng
Sun, Zhaojun
Li, Ran
Qian, Chen
Wei, Yiwei
Liu, Zhiyuan
Shi, Chuan
Sun, Maosong
Yang, Cheng
author_facet Li, Xin
Chen, Weize
Chu, Qizhi
Li, Haopeng
Sun, Zhaojun
Li, Ran
Qian, Chen
Wei, Yiwei
Liu, Zhiyuan
Shi, Chuan
Sun, Maosong
Yang, Cheng
contents The need to analyze graphs is ubiquitous across various fields, from social networks to biological research and recommendation systems. Therefore, enabling the ability of large language models (LLMs) to process graphs is an important step toward more advanced general intelligence. However, current LLM benchmarks on graph analysis require models to directly reason over the prompts describing graph topology, and are thus limited to small graphs with only a few dozens of nodes. In contrast, human experts typically write programs based on popular libraries for task solving, and can thus handle graphs with different scales. To this end, a question naturally arises: can LLMs analyze graphs like professionals? In this paper, we introduce ProGraph, a manually crafted benchmark containing 3 categories of graph tasks. The benchmark expects solutions based on programming instead of directly reasoning over raw inputs. Our findings reveal that the performance of current LLMs is unsatisfactory, with the best model achieving only 36% accuracy. To bridge this gap, we propose LLM4Graph datasets, which include crawled documents and auto-generated codes based on 6 widely used graph libraries. By augmenting closed-source LLMs with document retrieval and fine-tuning open-source ones on the codes, we show 11-32% absolute improvements in their accuracies. Our results underscore that the capabilities of LLMs in handling structured data are still under-explored, and show the effectiveness of LLM4Graph in enhancing LLMs' proficiency of graph analysis. The benchmark, datasets and enhanced open-source models are available at https://github.com/BUPT-GAMMA/ProGraph.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19667
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models
Li, Xin
Chen, Weize
Chu, Qizhi
Li, Haopeng
Sun, Zhaojun
Li, Ran
Qian, Chen
Wei, Yiwei
Liu, Zhiyuan
Shi, Chuan
Sun, Maosong
Yang, Cheng
Computation and Language
Artificial Intelligence
The need to analyze graphs is ubiquitous across various fields, from social networks to biological research and recommendation systems. Therefore, enabling the ability of large language models (LLMs) to process graphs is an important step toward more advanced general intelligence. However, current LLM benchmarks on graph analysis require models to directly reason over the prompts describing graph topology, and are thus limited to small graphs with only a few dozens of nodes. In contrast, human experts typically write programs based on popular libraries for task solving, and can thus handle graphs with different scales. To this end, a question naturally arises: can LLMs analyze graphs like professionals? In this paper, we introduce ProGraph, a manually crafted benchmark containing 3 categories of graph tasks. The benchmark expects solutions based on programming instead of directly reasoning over raw inputs. Our findings reveal that the performance of current LLMs is unsatisfactory, with the best model achieving only 36% accuracy. To bridge this gap, we propose LLM4Graph datasets, which include crawled documents and auto-generated codes based on 6 widely used graph libraries. By augmenting closed-source LLMs with document retrieval and fine-tuning open-source ones on the codes, we show 11-32% absolute improvements in their accuracies. Our results underscore that the capabilities of LLMs in handling structured data are still under-explored, and show the effectiveness of LLM4Graph in enhancing LLMs' proficiency of graph analysis. The benchmark, datasets and enhanced open-source models are available at https://github.com/BUPT-GAMMA/ProGraph.
title Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2409.19667