Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.04483 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908660688486400 |
|---|---|
| author | Luo, Zihan Song, Xiran Huang, Hong Lian, Jianxun Zhang, Chenhao Jiang, Jinqi Xie, Xing Jin, Hai |
| author_facet | Luo, Zihan Song, Xiran Huang, Hong Lian, Jianxun Zhang, Chenhao Jiang, Jinqi Xie, Xing Jin, Hai |
| contents | Improving the general capabilities of large language models (LLMs) is an active research topic. As a common data structure in many real-world domains, understanding graph data is a crucial part of advancing general intelligence. To this end, we propose a dynamic benchmark named GraphInstruct in this paper, which comprehensively includes 21 classical graph reasoning tasks, providing diverse graph generation pipelines and detailed intermediate reasoning steps for each sample. Based on GraphInstruct, we develop GraphSolver via efficient instruction-tuning, which demonstrates prominent graph understanding capability compared to other open-sourced LLMs. To further endow LLMs with multi-step graph reasoning capability, we propose a label-mask training strategy and build GraphSolver+, which leverages masked supervision on intermediate reasoning tokens to emphasize crucial node-identification signals. As one of the pioneering efforts to enhance the graph understanding and reasoning abilities of LLMs, extensive experiments have demonstrated the superiority of GraphSolver and GraphSolver+ over other LLMs. We sincerely hope GraphInstruct will facilitate further research on applying LLMs to graph-structured data. Our code and data are released publicly at: https://github.com/CGCL-codes/GraphInstruct. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04483 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability Luo, Zihan Song, Xiran Huang, Hong Lian, Jianxun Zhang, Chenhao Jiang, Jinqi Xie, Xing Jin, Hai Artificial Intelligence Computation and Language Improving the general capabilities of large language models (LLMs) is an active research topic. As a common data structure in many real-world domains, understanding graph data is a crucial part of advancing general intelligence. To this end, we propose a dynamic benchmark named GraphInstruct in this paper, which comprehensively includes 21 classical graph reasoning tasks, providing diverse graph generation pipelines and detailed intermediate reasoning steps for each sample. Based on GraphInstruct, we develop GraphSolver via efficient instruction-tuning, which demonstrates prominent graph understanding capability compared to other open-sourced LLMs. To further endow LLMs with multi-step graph reasoning capability, we propose a label-mask training strategy and build GraphSolver+, which leverages masked supervision on intermediate reasoning tokens to emphasize crucial node-identification signals. As one of the pioneering efforts to enhance the graph understanding and reasoning abilities of LLMs, extensive experiments have demonstrated the superiority of GraphSolver and GraphSolver+ over other LLMs. We sincerely hope GraphInstruct will facilitate further research on applying LLMs to graph-structured data. Our code and data are released publicly at: https://github.com/CGCL-codes/GraphInstruct. |
| title | GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2403.04483 |