ChatGPT Chemistry Assistant for Text Mining and the Prediction of MOF Synthesis
Kavli Energy NanoScience Institute · University of California, Berkeley · +1 more institution
Abstract
We use prompt engineering to guide ChatGPT in the automation of text mining of metal-organic framework (MOF) synthesis conditions from diverse formats and styles of the scientific literature. This effectively mitigates ChatGPT's tendency to hallucinate information, an issue that previously made the use of large language models (LLMs) in scientific fields challenging. Our approach involves the development of a workflow implementing three different processes for text mining, programmed by ChatGPT itself. All of them enable parsing, searching, filtering, classification, summarization, and data unification with different trade-offs among labor, speed, and accuracy. We deploy this system to extract 26 257 distinct…
Citation impact
- FWCI
- 42.70
- Percentile
- 100%
- References
- 59
Authors
5- ZZZhiling Zheng
Kavli Energy NanoScience Institute, University of California, Berkeley
- OZOufan Zhang
King Abdulaziz City for Science and Technology, Kavli Energy NanoScience Institute, University of California, Berkeley
- CBChristian Borgs
University of California, Berkeley
- JCJennifer Chayes
University of California, Berkeley
- OMOmar M. YaghiCorresponding
King Abdulaziz City for Science and Technology, Kavli Energy NanoScience Institute, University of California, Berkeley
Topics & keywords
- Workflow
- Automatic summarization
- Parsing
- Computer science
- Unification
- Process (computing)
- Automation
- Documentation
- Decent work and economic growth
Funding
- KFKavli Foundation
- CMCarnegie Mellon University
- ENEidgenössisches Nuklearsicherheitsinspektorat
- NINational Institutes of HealthAward: 5R01GM127627-04
- DADefense Advanced Research Projects AgencyAward: HR0011-21-C-0020
- ARAdvanced Research Projects Agency
- NINational Institute of General Medical SciencesAward: 5R01GM127627-04