MatExpert: Decomposing Materials Discovery By Mimicking Human Experts
Keywords: Material Discovery, Large Language Models (LLMs), Material Generation, Crystal Structure Generation, Contrastive Learning
TL;DR: We present MatExpert, a novel framework leveraging Large Language Models (LLMs) and contrastive learning to streamline material discovery like human expert workflows.
Abstract: Material discovery is a critical research area with profound implications for various industries. In this work, we introduce MatExpert, a novel framework that leverages Large Language Models (LLMs) and contrastive learning to accelerate the discovery and design of new solid-state materials. Inspired by the workflow of human materials design experts, our approach integrates three key stages: retrieval, transition, and generation. First, in the retrieval stage, MatExpert identifies an existing material that closely matches the desired criteria. Second, in the transition stage, MatExpert outlines the necessary modifications to transform this material formulation to meet specific requirements outlined by the initial user query. Third, in the generation state, MatExpert performs detailed computations and structural generation to create a new material based on the provided information. Our experimental results demonstrate that MatExpert outperforms state-of-the-art methods in material generation tasks, achieving superior performance across various metrics including validity, distribution, and stability. As such, MatExpert represents a meaningful advancement in computational material discovery using langauge-based generative models.
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 11344
Loading