TXL Fusion: A Hybrid Machine Learning Framework Integrating Chemical Heuristics and Large Language Models for Topological Materials Discovery
Authors:
Open Access
- 29 July 2026
- journal article
- research article
- Published by Wiley in Advanced Functional Materials
- Vol. 36 (69) , e29788
Abstract
Topological materials, including topological insulators (TIs) and topological semimetals (TSMs), offer promising platforms for quantum, spintronic, and low‐dissipation electronic technologies. Their discovery, however, remains constrained by the high cost of first‐principles calculations and the slow, resource‐intensive nature of experimental validation. Here, we introduce TXL Fusion, a hybrid machine‐learning framework that integrates chemically inspired heuristics, physically interpretable numerical descriptors, and large language model (LLM)‐derived semantic embeddings for topological‐materials classification and discovery. By combining space‐group symmetry, electron‐count and orbital descriptors, composition‐derived topological heuristics, and physics‐aware semantic representations, TXL Fusion classifies materials into trivial, TSM, and TI categories with improved overall performance and enhanced minority‐class TI recognition relative to conventional descriptor‐based baselines. The model further serves as a high‐throughput pre‐screening tool for external discovery spaces, rapidly prioritizing candidates before expensive first‐principles or experimental validation. Representative TXL‐prioritized candidates were subsequently supported by density functional theory (DFT) calculations, demonstrating the practical value of the framework for reducing discovery cost. By uniting symbolic chemical rules, statistical learning, and language‐based representations, TXL Fusion provides a scalable and interpretable strategy for accelerating the discovery of next‐generation topological and quantum materials.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (W2433037)
- Natural Science Foundation of Anhui Province (2408085QA002)
This publication has 39 references indexed in Scilit:
- LLM-Prop: predicting the properties of crystalline materials using large language modelsnpj Computational Materials, 2025
- Harnessing Large Language Models to Collect and Analyze Metal–Organic Framework Property Data SetJournal of the American Chemical Society, 2025
- Large Language Models for Inorganic Synthesis PredictionsJournal of the American Chemical Society, 2024
- Leveraging language representation for materials exploration and discoverynpj Computational Materials, 2024
- Accurate, interpretable predictions of materials properties within transformer language modelsPatterns, 2023
- Topogivity: A Machine-Learned Chemical Rule for Discovering Topological MaterialsNano Letters, 2023
- Machine‐Learning Spectral Indicators of TopologyAdvanced Materials, 2022
- Topological quantum chemistryNature, 2017
- Symmetry-based indicators of band topology in the 230 space groupsNature Communications, 2017
- The space group classification of topological band-insulatorsNature Physics, 2012