MaTableGPT: GPT‐Based Table Data Extractor from Materials Science Literature
[1];
[2];
[2]
- Computational Science Research Center Korea Institute of Science and Technology Seoul 02792 Republic of Korea, Department of Materials Science and Engineering Korea University Seoul 02841 Republic of Korea
- Computational Science Research Center Korea Institute of Science and Technology Seoul 02792 Republic of Korea
- Global Security Computing Applications Division Lawrence Livermore National Laboratory Livermore CA 94550 USA
- Department of Materials Science and Engineering Korea University Seoul 02841 Republic of Korea
- Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore CA 94550 USA
- Materials Science Division Lawrence Livermore National Laboratory Livermore CA 94550 USA
Abstract Efficiently extracting data from tables in the scientific literature is pivotal for building large‐scale databases. However, the tables reported in materials science papers exist in highly diverse forms; thus, rule‐based extractions are an ineffective approach. To overcome this challenge, the study presents MaTableGPT, which is a GPT‐based table data extractor from the materials science literature. MaTableGPT features key strategies of table data representation and table splitting for better GPT comprehension and filtering hallucinated information through follow‐up questions. When applied to a vast volume of water splitting catalysis literature, MaTableGPT achieves an extraction accuracy (total F1 score) of up to 96.8%. Through comprehensive evaluations of the GPT usage cost, labeling cost, and extraction accuracy for the learning methods of zero‐shot, few‐shot, and fine‐tuning, the study presents a Pareto‐front mapping where the few‐shot learning method is found to be the most balanced solution owing to both its high extraction accuracy (total F1 score >95%) and low cost (GPT usage cost of 5.97 US dollars and labeling cost of 10 I/O paired examples). The statistical analyses conducted on the database generated by MaTableGPT revealed valuable insights into the distribution of the overpotential and elemental utilization across the reported catalysts in the water splitting literature.
- Sponsoring Organization:
- USDOE
- OSTI ID:
- 2506940
- Journal Information:
- Advanced Science, Journal Name: Advanced Science Journal Issue: 16 Vol. 12; ISSN 2198-3844
- Publisher:
- Wiley Blackwell (John Wiley & Sons)Copyright Statement
- Country of Publication:
- Germany
- Language:
- English
Similar Records
Cybersecurity Automated Information Extraction Techniques: Drawbacks of Current Methods, and Enhanced Extractors
Extracting Material Property Measurements from Scientific Literature with Limited Annotations