TY - GEN
T1 - InstructGraph
T2 - Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024
AU - Wang, Jianing
AU - Wu, Junda
AU - Hou, Yupeng
AU - Liu, Yao
AU - Gao, Ming
AU - McAuley, Julian
N1 - Publisher Copyright:
© 2024 Association for Computational Linguistics.
PY - 2024
Y1 - 2024
N2 - Do current large language models (LLMs) better solve graph reasoning and generation tasks with parameter updates? In this paper, we propose InstructGraph, a framework that empowers LLMs with the abilities of graph reasoning and generation by instruction tuning and preference alignment. Specifically, we first propose a structured format verbalizer to unify all graph data into a universal code-like format, which can simply represent the graph without any external graph-specific encoders. Furthermore, a graph instruction tuning stage is introduced to guide LLMs in solving graph reasoning and generation tasks. Finally, we identify potential hallucination problems in graph tasks and sample negative instances for preference alignment, the target of which is to enhance the output's reliability of the model. Extensive experiments across multiple graph-centric tasks exhibit that InstructGraph can achieve the best performance and outperform GPT-4 and LLaMA2 by more than 13% and 38%, respectively..
AB - Do current large language models (LLMs) better solve graph reasoning and generation tasks with parameter updates? In this paper, we propose InstructGraph, a framework that empowers LLMs with the abilities of graph reasoning and generation by instruction tuning and preference alignment. Specifically, we first propose a structured format verbalizer to unify all graph data into a universal code-like format, which can simply represent the graph without any external graph-specific encoders. Furthermore, a graph instruction tuning stage is introduced to guide LLMs in solving graph reasoning and generation tasks. Finally, we identify potential hallucination problems in graph tasks and sample negative instances for preference alignment, the target of which is to enhance the output's reliability of the model. Extensive experiments across multiple graph-centric tasks exhibit that InstructGraph can achieve the best performance and outperform GPT-4 and LLaMA2 by more than 13% and 38%, respectively..
UR - https://www.scopus.com/pages/publications/85204656266
U2 - 10.18653/v1/2024.findings-acl.801
DO - 10.18653/v1/2024.findings-acl.801
M3 - 会议稿件
AN - SCOPUS:85204656266
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 13492
EP - 13510
BT - The 62nd Annual Meeting of the Association for Computational Linguistics
A2 - Ku, Lun-Wei
A2 - Martins, Andre
A2 - Srikumar, Vivek
PB - Association for Computational Linguistics (ACL)
Y2 - 11 August 2024 through 16 August 2024
ER -