Is the laboratory report dead? AI and ChatGPT
Jack T. H. Wang A *A School of Chemistry and Molecular Biosciences, The University of Queensland, Brisbane, Qld 4072, Australia.
Assoc. Prof. Jack Wang is a teaching-focused microbiologist at The University of Queensland. His work focuses on undergraduate research and technology-enabled assessment in science education. He was the recipient of the 2020 ASM David White Teaching Excellence award, and was named the 2020 Australian University Teacher of the year. |
Microbiology Australia 44(3) 144-148 https://doi.org/10.1071/MA23042
Submitted: 31 May 2023 Accepted: 20 June 2023 Published: 4 July 2023
© 2023 The Author(s) (or their employer(s)). Published by CSIRO Publishing on behalf of the ASM. This is an open access article distributed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND)
Abstract
The launch of ChatGPT and artificial intelligence (AI) platforms capable of generating written responses to a vast range of text-based queries has transformed the conceptualisation of assessment in education. Apart from its potential for misuse in test and examinations, the laboratory report in Science Education may be vulnerable to AI-disruption. This article outlines five text-based prompts that educators can use to assess the quality of AI-generated output in scientific writing. When used to query the freely accessible version of ChatGPT (GPT-3.5) in June 2023, these prompts revealed its ability to produce written work that showcases high-level organisation of concepts relevant to a scientific topic. However, these AI-generated responses remain generalised, lacking specificity and without effective integration of peer-reviewed scientific literature. As these generative AI platforms continue to improve, educators can use this series of prompts to evaluate the quality of AI output and adapt the assessment criteria for this new era in scientific writing.
Keywords: artificial intelligence, assessment, Bloom’s taxonomy, ChatGPT, laboratory report.
References
[1] Yeadon, W et al.. (2023) The death of the short-form physics essay in the coming AI revolution. Phys Educ 58, 035027.| The death of the short-form physics essay in the coming AI revolution.Crossref | GoogleScholarGoogle Scholar |
[2] Gilson, A et al.. (2023) How does ChatGPT perform on the United States Medical Licensing Examination? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ 9, e45312.
| How does ChatGPT perform on the United States Medical Licensing Examination? The implications of large language models for medical education and knowledge assessment.Crossref | GoogleScholarGoogle Scholar |
[3] Merkel, S (2012) The development of curricular guidelines for introductory microbiology that focus on understanding. J Microbiol Biol Educ 13, 32–38.
| The development of curricular guidelines for introductory microbiology that focus on understanding.Crossref | GoogleScholarGoogle Scholar |
[4] Burke, C et al.. (2016) Threshold learning outcomes for a microbiology major. Microbiol Aust 37, 93–97.
| Threshold learning outcomes for a microbiology major.Crossref | GoogleScholarGoogle Scholar |
[5] Crowe, A et al.. (2008) Biology in bloom: implementing Bloom’s taxonomy to enhance student learning in biology. CBE Life Sci Educ 7, 368–381.
| Biology in bloom: implementing Bloom’s taxonomy to enhance student learning in biology.Crossref | GoogleScholarGoogle Scholar |
[6] Sanderson, K (2023) GPT-4 is here: what scientists think. Nature 615, 773.
| GPT-4 is here: what scientists think.Crossref | GoogleScholarGoogle Scholar |
[7] Alkaissi, H and McFarlane, SI (2023) Artificial hallucinations in ChatGPT: implications in scientific writing. Cureus 15, e35179.
| Artificial hallucinations in ChatGPT: implications in scientific writing.Crossref | GoogleScholarGoogle Scholar |
[8] Thorp, HH (2023) ChatGPT is fun, but not an author. Science 379, 313.
| ChatGPT is fun, but not an author.Crossref | GoogleScholarGoogle Scholar |
[9] Lin, JC et al.. (2023) Comparison of GPT-3.5, GPT-4, and human user performance on a practice ophthalmology written examination. Eye , 1–2.
| Comparison of GPT-3.5, GPT-4, and human user performance on a practice ophthalmology written examination.Crossref | GoogleScholarGoogle Scholar |
[10] Fergus, S et al.. (2023) Evaluating academic answers generated using chatgpt. J Chem Educ 100, 1672–1675.
| Evaluating academic answers generated using chatgpt.Crossref | GoogleScholarGoogle Scholar |
