Francis, Nigel ![]() ![]() |
![]() |
PDF
- Presentation
Download (1MB) |
Official URL: https://2025aseannualconf.sched.com/event/1en7v/be...
Abstract
Our project assesses the ability of Generative AI in two key areas. 1. How well does Generative AI construct evidence based scientific text compared to humans? Our assessment includes the impact of different of AI tools, length of prose and few-shot prompting. 2. How well can AI grade and provide feedback against a set of criteria when compared to human assessors. This includes an evaluation of the ability of AI to assess its own product.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Date Type: | Published Online |
Status: | Published |
Schools: | Biosciences |
Date of Acceptance: | 29 July 2024 |
Last Modified: | 14 Jan 2025 17:45 |
URI: | https://orca.cardiff.ac.uk/id/eprint/175263 |
Actions (repository staff only)
![]() |
Edit Item |