Generative AI or Large Language Models, such as ChatGPT, and other machine learning tools, are starting to be used in reviews for a range of tasks like screening and data extraction.
While they can be useful to speed up parts of the process and save time, understanding the bias and limitations of tools is important.
For example, the accuracy of outputs, the time required to learn how to use the tool and ‘train’ it, and the need for a person to manually check and correct errors needs to be carefully considered.
For more information on the use of Generative AI, see the Federation University guide to Generative artificial intelligence: Use at university.
Qureshi, R., Shaughnessy, D., Gill, K. A. R., Robinson, K. A., Li, T., & Agai, E. (2023). Are ChatGPT and large language models “the answer” to bringing us closer to systematic review automation? Systematic Reviews, 12(1), 72. https://doi.org/10.1186/s13643-023-02243-z
Blaizot, A., Veettil, S. K., Saidoung, P., Moreno-Garcia, C. F., Wiratunga, N., Aceves-Martins, M., Lai, N. M., & Chaiyakunapruk, N. (2022). Using artificial intelligence methods for systematic review in health sciences: A systematic review. Research Synthesis Methods, 13(3), 353-362. https://doi.org/https://doi.org/10.1002/jrsm.1553
  |
Federation University Australia acknowledges the Traditional Custodians of the lands and waters where our campuses, centres and field stations are located and we pay our respects to Elders past and present, and extend our respect to all Aboriginal and Torres Strait Islander and First Nations Peoples. |