Scholarlink

<p>The ability to generate crystal structures directly from textual descriptions marks a pivotal advancement in materials informatics and underscores the emerging role of large language models (LLMs) in inverse design. In this work, we introduce CrysText, a text-conditioned framework that generates crystal structures in Crystallographic Information File (CIF) format from natural language prompts specifying composition and space group. Leveraging LLaMA-3.1-8B and Mistral-7B-v0.3 fine-tuned using Quantized Low-Rank Adaptation (QLoRA), our approach enables the efficient and scalable generation of CIF-formatted structures directly from input descriptions, eliminating the need for post-processing with rapid inference. Evaluations on the MP-20 benchmark demonstrate high structural match rates and low RMSE values, confirming the model’s ability to generate physically consistent crystal structures aligned with compositional and symmetry constraints. By incorporating energy above the convex hull as a conditioning parameter, CrysText further demonstrates the ability to generate thermodynamically stable novel materials. We subsequently extend this framework with CrysText-RL, which integrates Group Relative Policy Optimization (GRPO) to provide reinforcement learning feedback directly on generated CIF outputs via group-based normalized rewards. CrysText-RL achieves additional improvements over the supervised CrysText model in terms of composition and space group satisfiability and structure match rate. This work establishes a scalable paradigm for text-driven crystal structure generation, demonstrating that both supervised fine-tuning and reinforcement learning enable a pathway towards accelerated materials discovery.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CrysText: A Generative AI Approach for Text-Conditioned Crystal Structure Generation Using LLM

  • 期刊论文

  • 发表日期：

    2026年3月21日

查看全文
  • Trupti Mohanty,
  • Maitrey Mehta,
  • Hasan M. Sayeed,
  • Bat-El Oded,
  • Itay Pitussi,
  • Arie Borenstein,
  • Vivek Srikumar,
  • Taylor D. Sparks

摘要

The ability to generate crystal structures directly from textual descriptions marks a pivotal advancement in materials informatics and underscores the emerging role of large language models (LLMs) in inverse design. In this work, we introduce CrysText, a text-conditioned framework that generates crystal structures in Crystallographic Information File (CIF) format from natural language prompts specifying composition and space group. Leveraging LLaMA-3.1-8B and Mistral-7B-v0.3 fine-tuned using Quantized Low-Rank Adaptation (QLoRA), our approach enables the efficient and scalable generation of CIF-formatted structures directly from input descriptions, eliminating the need for post-processing with rapid inference. Evaluations on the MP-20 benchmark demonstrate high structural match rates and low RMSE values, confirming the model’s ability to generate physically consistent crystal structures aligned with compositional and symmetry constraints. By incorporating energy above the convex hull as a conditioning parameter, CrysText further demonstrates the ability to generate thermodynamically stable novel materials. We subsequently extend this framework with CrysText-RL, which integrates Group Relative Policy Optimization (GRPO) to provide reinforcement learning feedback directly on generated CIF outputs via group-based normalized rewards. CrysText-RL achieves additional improvements over the supervised CrysText model in terms of composition and space group satisfiability and structure match rate. This work establishes a scalable paradigm for text-driven crystal structure generation, demonstrating that both supervised fine-tuning and reinforcement learning enable a pathway towards accelerated materials discovery.