A Generation Framework with Strict Constraints for Crystal Materials Design
This work addresses the need for efficient and reliable crystal design in fields like new energy and semiconductors, offering a significant improvement over random sampling methods.
The paper tackles the problem of generating crystal materials with specific properties by introducing a constrained generation framework that uses large language models to produce intermediate constraints, resulting in a probability of meeting target properties more than twice that of existing approaches and nearly 100% adherence to predefined chemical composition.
The design of crystal materials plays a critical role in areas such as new energy development, biomedical engineering, and semiconductors. Recent advances in data-driven methods have enabled the generation of diverse crystal structures. However, most existing approaches still rely on random sampling without strict constraints, requiring multiple post-processing steps to identify stable candidates with the desired physical and chemical properties. In this work, we present a new constrained generation framework that takes multiple constraints as input and enables the generation of crystal structures with specific chemical and properties. In this framework, intermediate constraints, such as symmetry information and composition ratio, are generated by a constraint generator based on large language models (LLMs), which considers the target properties. These constraints are then used by a subsequent crystal structure generator to ensure that the structure generation process is under control. Our method generates crystal structures with a probability of meeting the target properties that is more than twice that of existing approaches. Furthermore, nearly 100% of the generated crystals strictly adhere to predefined chemical composition, eliminating the risks of supply chain during production.