Peer-reviewedCC BYAI Agent
From unstructured to structured: opportunities, risks and engineering practices for LLM-based data extraction in chemistry and materials
- 1Beijing Key Laboratory of Intelligent Design and Manufacturing for Hydrogen Energy Materials , Beijing University of Chemical Technology , Beijing 100029 , China
- 2Deep Intelligence Experiment Technology ( Beijing) Co., Ltd. , Beijing 100029 , China
- 3Correspondence to: Prof. Haoxiang Xu, Prof. Daojian Cheng, Beijing Key Laboratory of Intelligent Design and Manufacturing for Hydrogen Energy Materials, Beijing University of Chemical Technology, Beijing 100029, China. E-mail: [email protected]; [email protected]
Abstract
opportunities, risks and engineering practices for LLM-based data
Related
- PolyReader: an agentic LLM pipeline for extracting structured data from unstructured polymer scientific literature
- InAs Quantum Dots for Infrared Optoelectronics: Interface Engineering, Device Performance, and Emerging Opportunities
- Gaps, challenges, and opportunities of sodium borohydride alcoholysis for hydrogen
- PET Imaging of Sphingolipid Signaling: Current Radiotracers, Translational Gaps, and Opportunities in Neurodegeneration and Oncology
- Coarse-Graining in Drug Discovery: Opportunities and Challenges for Martini 3 in Small-Molecule Binding
BibTeX
@article{chen2026from,
title = {{From unstructured to structured: opportunities, risks and engineering practices for LLM-based data extraction in chemistry and materials}},
author = {Weijian Chen and Haoxiang Xu and Daojian Cheng},
journal = {AI Agent},
year = {2026},
month = jun,
doi = {10.20517/aiagent.2026.06},
url = {https://doi.org/10.20517/aiagent.2026.06},
note = {CC BY},
}
RIS
TY - JOUR
TI - From unstructured to structured: opportunities, risks and engineering practices for LLM-based data extraction in chemistry and materials
AU - Weijian Chen
AU - Haoxiang Xu
AU - Daojian Cheng
PY - 2026
DA - 2026/06/03
JO - AI Agent
DO - 10.20517/aiagent.2026.06
UR - https://doi.org/10.20517/aiagent.2026.06
AB - opportunities, risks and engineering practices for LLM-based data
SN - 3070-3719
ER -