aLLoyM: A large language model for alloy phase diagram prediction

TL;DR

aLLoyM is a specialized large language model trained on alloy phase diagram data, capable of generating and understanding phase diagrams, thus aiding materials discovery.

Contribution

This work introduces aLLoyM, a fine-tuned LLM for alloy phase diagrams, with publicly available datasets and models to advance materials science research.

Findings

Fine-tuning improves phase diagram question-answering accuracy.

aLLoyM can generate novel phase diagrams from component data.

Public release of datasets and models supports further research.

Abstract

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 exhibits the ability to generate novel phase diagrams from its components alone, underscoring its potential to accelerate the discovery of previously unexplored 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.