Large language models in materials science and the need for open-source approaches

TL;DR

This paper reviews how large language models are transforming materials science, emphasizing the importance of open-source models for transparency, reproducibility, and community-driven scientific discovery.

Contribution

It highlights the potential of open-source LLMs in materials science and demonstrates their performance parity with commercial models through benchmark results.

Findings

Open-source LLMs match commercial model performance

Open-source models offer greater transparency and reproducibility

Open-source models are cost-effective and privacy-preserving

Abstract

Large language models (LLMs) are rapidly transforming materials science. This review examines recent LLM applications across the materials discovery pipeline, focusing on three key areas: mining scientific literature , predictive modelling, and multi-agent experimental systems. We highlight how LLMs extract valuable information such as synthesis conditions from text, learn structure-property relationships, and can coordinate agentic systems integrating computational tools and laboratory automation. While progress has been largely dependent on closed-source commercial models, our benchmark results demonstrate that open-source alternatives can match performance while offering greater transparency, reproducibility, cost-effectiveness, and data privacy. As open-source models continue to improve, we advocate their broader adoption to build accessible, flexible, and community-driven AI platforms for scientific discovery.