A comparative analysis of text-to-image generative AI models in scientific contexts: a case study on nuclear power
Veda Joynt, Jacob Cooper, Naman Bhargava, Katie Vu, O. Hwang Kwon, Todd R. Allen, Aditi Verma, Majdi I. Radaideh · 2024
Read A comparative analysis of text-to-image generative AI models in scientific contexts: a case study on nuclear power by Veda Joynt, Jacob Cooper, Naman Bhargava, Katie Vu, O. Hwang Kwon, Todd R. Allen, Aditi Verma, Majdi I. Radaideh (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11621808.txt.
Description
Veda Joynt and co-authors compared twenty AI image generators on nuclear energy topics, in a 2024 study. The team asks whether text-to-image tools could help the public grasp low-carbon energy, using nuclear power as the test case. Generators were scored on both general and technical scientific prompts.
Three tools, named in the paper, handled general nuclear prompts promisingly. All fell short in the same three ways, though. They mangled technical details of energy systems. They copied gender and workplace biases from their training data. And they misdrew Indigenous landscapes, places long used for resource extraction and waste storage. The authors call for specialized generators built for science communication, so that public engagement rests on accurate and fair images.
Catalog record
| CREATOR | Veda Joynt, Jacob Cooper, Naman Bhargava, Katie Vu, O. Hwang Kwon, Todd R. Allen, Aditi Verma, Majdi I. Radaideh |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 81 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |