Scholarlink

<p>Large language models (LLMs) are general-purpose tools with wide-ranging applications, including in materials science. In this work, we introduce aLLoyM, a fine-tuned LLM specifically trained on alloy compositions, temperatures, and their corresponding phase information. To develop aLLoyM, we curated question-and-answer (Q&amp;A) pairs for binary and ternary phase diagrams using the open-source Computational Phase Diagram Database (CPDDB) and assessments based on CALPHAD (CALculation of PHAse Diagrams). We fine-tuned Mistral, an open-source pre-trained LLM, for two distinct Q&amp;A formats: multiple-choice and short-answer. Benchmark evaluations demonstrate that fine-tuning substantially enhances performance on multiple-choice phase diagram questions. Moreover, the short-answer model of aLLoyM can generate novel phase diagrams from its components alone, suggesting that it may aid the discovery of new materials systems. To promote further research and adoption, we have publicly released the short-answer fine-tuned version of aLLoyM, along with the complete benchmarking Q&amp;A dataset, on Hugging Face.</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

aLLoyM: a large language model for alloy phase diagram prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月22日

查看全文
  • Yuna Oikawa,
  • Guillaume Deffrennes,
  • Rintaro Shimayoshi,
  • Taichi Abe,
  • Ryo Tamura,
  • Koji Tsuda

摘要

Large language models (LLMs) are general-purpose tools with wide-ranging applications, including in materials science. In this work, we introduce aLLoyM, a fine-tuned LLM specifically trained on alloy compositions, temperatures, and their corresponding phase information. To develop aLLoyM, we curated question-and-answer (Q&A) pairs for binary and ternary phase diagrams using the open-source Computational Phase Diagram Database (CPDDB) and assessments based on CALPHAD (CALculation of PHAse Diagrams). We fine-tuned Mistral, an open-source pre-trained LLM, for two distinct Q&A formats: multiple-choice and short-answer. Benchmark evaluations demonstrate that fine-tuning substantially enhances performance on multiple-choice phase diagram questions. Moreover, the short-answer model of aLLoyM can generate novel phase diagrams from its components alone, suggesting that it may aid the discovery of new materials systems. To promote further research and adoption, we have publicly released the short-answer fine-tuned version of aLLoyM, along with the complete benchmarking Q&A dataset, on Hugging Face.