Evaluating large language models for health-related text classification tasks with public social media data
By leveraging the data augmentation strategy, we can harness the power of LLMs to develop smaller, more effective domain-specific NLP models. Using LLM-annotated data without human guidance for training lightweight supervised classification models is an ineffective strategy. However, LLM, as a zero-shot classifier, shows promise in excluding false negatives and potentially reducing the human effort required for data annotation.
Authors
- Mohammed Ali Al-Garadi (ORCID: https://orcid.org/0000-0002-6991-2687)
- Abeed Sarker (ORCID: https://orcid.org/0000-0001-7358-544X)
- Yuting Guo (ORCID: https://orcid.org/0000-0002-8919-0888)
- Anthony Ovadje
Institutions
- Georgia Institute of Technology (US)
- Emory University (US)
- Vanderbilt University (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2024-08-08
- DOI
- https://doi.org/10.1093/jamia/ocae210
- Citations
- 47
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 16.33
Funders
- National Institutes of Health
- National Institute on Drug Abuse