GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models

TL;DR

GraCoRe is a comprehensive benchmark designed to evaluate large language models' abilities in understanding and reasoning about various types of graphs, revealing insights into their strengths and limitations.

Contribution

The paper introduces GraCoRe, a hierarchical, multi-faceted benchmark for systematic assessment of LLMs' graph comprehension and reasoning capabilities across diverse graph types.

Findings

OpenAI o1 model shows strong comprehension and reasoning abilities.

Semantic enrichment improves reasoning performance.

Node ordering affects task success and performance.

Abstract

Evaluating the graph comprehension and reasoning abilities of Large Language Models (LLMs) is challenging and often incomplete. Existing benchmarks focus primarily on pure graph understanding, lacking a comprehensive evaluation across all graph types and detailed capability definitions. This paper presents GraCoRe, a benchmark for systematically assessing LLMs' graph comprehension and reasoning. GraCoRe uses a three-tier hierarchical taxonomy to categorize and test models on pure graph and heterogeneous graphs, subdividing capabilities into 10 distinct areas tested through 19 tasks. Our benchmark includes 11 datasets with 5,140 graphs of varying complexity. We evaluate four closed-source and eight open-source LLMs, conducting thorough analyses from both ability and task perspectives. Key findings reveal that OpenAI o1 model has amazing comprehension and reasoning capabilities, semantic enrichment enhances reasoning performance, node ordering impacts task success, and the ability to process longer texts does not necessarily improve graph comprehension or reasoning.GraCoRe is open-sourced at https://github.com/ZIKEYUAN/GraCoRe