Mat-Instructions: A Large-Scale Inorganic Material Instruction Dataset for Large Language Models

Liu, Ke; Gao, Shangde; Fu, Yichao; Wu, Xiaoliang; Tong, Shuo; Rajan, Ajitha; Xu, Hao

doi:10.24963/ijcai.2025/1089

Mat-Instructions: A Large-Scale Inorganic Material Instruction Dataset for Large Language Models

Ke Liu, Shangde Gao, Yichao Fu, Xiaoliang Wu, Shuo Tong, Ajitha Rajan, Hao Xu

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 9799-9807.

https://doi.org/10.24963/ijcai.2025/1089

Keywords

Multidisciplinary Topics and Applications: General

Abstract

Recent advancements in large language models (LLMs) have revolutionized research discovery across various scientific disciplines, including materials science. The discovery of novel materials, particularly crystal materials, is essential for achieving sustainable development goals (SDGs), as they drive breakthroughs in climate change mitigation, clean and affordable energy, and the promotion of industrial innovation. However, unlocking the full potential of LLMs in materials research remains challenging due to the lack of high-quality, diverse, and instruction-based datasets. Such datasets are crucial for guiding these models in understanding and predicting the structure, property, and function of materials across various tasks. To address this limitation, we introduce Mat-Instruction, a large-scale inorganic material instruction dataset, specifically designed to unlock the potential of LLMs in materials science. Extensive experiments on fine-tuning LLaMA with our Mat-Instruction dataset demonstrate its effectiveness in advancing progress for materials science. The code and dataset are available at https://github.com/zjuKeLiu/Mat-Instructions

Ke Liu, Shangde Gao, Yichao Fu, Xiaoliang Wu, Shuo Tong, Ajitha Rajan, and Hao Xu. 2025. Mat-Instructions: A Large-Scale Inorganic Material Instruction Dataset for Large Language Models. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 9799–9807. https://doi.org/10.24963/ijcai.2025/1089

@inproceedings{ijcai2025p1089,
  title     = {Mat-Instructions: A Large-Scale Inorganic Material Instruction Dataset for Large Language Models},
  author    = {Liu, Ke and Gao, Shangde and Fu, Yichao and Wu, Xiaoliang and Tong, Shuo and Rajan, Ajitha and Xu, Hao},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {9799--9807},
  year      = {2025},
  month     = {8},
  note      = {AI and Social Good},
  doi       = {10.24963/ijcai.2025/1089},
  url       = {https://doi.org/10.24963/ijcai.2025/1089},
}

TY  - CPAPER
TI  - Mat-Instructions: A Large-Scale Inorganic Material Instruction Dataset for Large Language Models
AU  - Liu, Ke
AU  - Gao, Shangde
AU  - Fu, Yichao
AU  - Wu, Xiaoliang
AU  - Tong, Shuo
AU  - Rajan, Ajitha
AU  - Xu, Hao
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 9799
EP  - 9807
DO  - 10.24963/ijcai.2025/1089
UR  - https://doi.org/10.24963/ijcai.2025/1089
ER  -