Ten simple rules for optimal and careful use of generative AI in science
Modern AI technologies leverage natural language processing (NLP), a subfield of AI dedicated to understanding, interpreting, and generating human language for developing large language models (LLMs), which have significantly advanced the capabilities of AI systems. These models can perform complex language tasks such as text generation, summarization, translation, and sentiment analysis, with unprecedented accuracy. The two main kinds of pre-training LLMs are the BERT-like models (e.g., BioBERT, proteinBERT, and PubMedBERT used primarily for language understanding; and the GPT-like models (e.g., BioGPT and ChatGPT-4o) used primarily for language generation
Authors
- Diogo Vieira da Silva Pellegrina (ORCID: https://orcid.org/0000-0001-6423-5093)
- Tamer Mansour (ORCID: https://orcid.org/0000-0002-4747-4241)
- Kumar Selvarajoo (ORCID: https://orcid.org/0000-0002-0314-9666)
- Mohamed Helmy (ORCID: https://orcid.org/0000-0002-9561-7956)
- Lingling Jin (ORCID: https://orcid.org/0000-0002-4586-2347)
- Amr Alhossary (ORCID: https://orcid.org/0000-0002-4470-5817)
Institutions
- Wesleyan University (US)
- Agency for Science, Technology and Research (SG)
- Mansoura University (EG)
- National University of Singapore (SG)
- Nanyang Technological University (SG)
- University of Saskatchewan (CA)
- Bioinformatics Institute (SG)
- Idaho State Department of Agriculture (US)
- University of California, Davis (US)
Publication Details
- Journal
- PLoS Computational Biology
- Published
- 2025-10-28
- DOI
- https://doi.org/10.1371/journal.pcbi.1013588
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62