Document is current
Any future updates will be listed below
-
Authors
Zhang, Yingbo
Ren, Shumin
Wang, Jiao
Lu, Junyu
Wu, Cong
He, Mengqiao
Liu, Xingyun
Wu, Rongrong
Zhao, Jing
Zhan, Chaoying
Du, Dan
Zhan, Zhajun
Singla, Rajeev K.
Shen, Bairong https://orcid.org/0000-0003-2899-1531
-
Funding
Funding for this research was provided by:
National Natural Science Foundation of China (32070671)
National Natural Science Foundation of China (32270690)
Natural Science Foundation of Hainan Province (820MS102)
Special Fund for Agro-scientific Research in the Public Interest (1630032020031)
- License Information
-
More Information
Article History
Accepted: 11 November 2024
First Online: 20 December 2024
Declarations
:
: This study was supported by the National Natural Science Foundation of China (32270690 and 32070671, Natural Science Foundation of Hainan Province of China (820MS102), and a special fund for agro-scientific research in the public interest (1630032020031).
: YZ, SR, JW, JL, CW, MH, XL, RW, JZ, CZ, DD, ZZ, RKS and BS have no conflicts of interest to declare.
: The dataset and its instructions have been uploaded to Huganeface () and Github (), and all users can download and reuse them from Huganeface and Github. The results and scores based on GPT-3.5 and GPT-4 can be downloaded from the attachments of this manuscript.
: Not applicable.
: BS conceived the project.BS and YZ initially designed the entire workflow, and SR, JW, and RKS, among others, extensively reviewed and discussed the rationality of the entire paper framework, providing modification suggestions. BS, RKS, DD, and ZZ designed the pharmacology-LLM-test-set, while YZ and XL constructed the large-scale model test set. SR, JW, and XL collected GPT-3.5 and GPT-4 evaluation results. BS, YZ, RKS, DD, and ZZ reviewed and scored the results. YZ, SR, JL, MH, RW, and CZ analyzed the data results. YZ drafted the initial manuscript, and SR, JZ, and CW edited it. All authors participated in the discussion of the results.
