A Prompt for Generating Script Concordance Test Using ChatGPT, Claude, and Llama Large Language Model Chatbots
Medical education always evolves to incorporate more tools for specific needs in assessing clinical reasoning skills. Among these tools, Script Concordance Test (SCT) has a particular importance due to its focus on assessing decision-making in uncertain clinical situations. However, development of...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidad de Murcia
2024-05-01
|
| Series: | Revista Española de Educación Médica |
| Subjects: | |
| Online Access: | https://revistas.um.es/edumed/article/view/612381 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823864493580484608 |
|---|---|
| author | Yavuz Selim Kıyak Emre Emekli |
| author_facet | Yavuz Selim Kıyak Emre Emekli |
| author_sort | Yavuz Selim Kıyak |
| collection | DOAJ |
| description |
Medical education always evolves to incorporate more tools for specific needs in assessing clinical reasoning skills. Among these tools, Script Concordance Test (SCT) has a particular importance due to its focus on assessing decision-making in uncertain clinical situations. However, development of SCT items is effortful. Artificial intelligence tools, such as large language models, offer significant benefits. These models are already used for generating multiple-choice questions, and their use in generating SCTs offers great promise. However, this requires well-designed prompts to generate SCTs. This article proposes a generic prompt for the ChatGPT-4, Claude 3, Llama 3, and ChatGPT-4o large language model chatbots to generate SCTs, which can be tailored to various fields of medicine and different stages of medical education. It can help to streamline the development process of SCTs. Initial findings are promising, and there is a need for generating SCTs using large language models and conducting research to assess the quality of SCTs.
|
| format | Article |
| id | doaj-art-213c42eaf4bd4032beaec32dc058ab0a |
| institution | Kabale University |
| issn | 2660-8529 |
| language | English |
| publishDate | 2024-05-01 |
| publisher | Universidad de Murcia |
| record_format | Article |
| series | Revista Española de Educación Médica |
| spelling | doaj-art-213c42eaf4bd4032beaec32dc058ab0a2025-02-08T22:17:51ZengUniversidad de MurciaRevista Española de Educación Médica2660-85292024-05-0153A Prompt for Generating Script Concordance Test Using ChatGPT, Claude, and Llama Large Language Model ChatbotsYavuz Selim Kıyak0https://orcid.org/0000-0002-5026-3234Emre Emekli1https://orcid.org/0000-0001-5989-1897Gazi University Faculty of MedicineDepartment of Radiology, Faculty of Medicine, Eskişehir Osmangazi University, Eskişehir, Turkey Medical education always evolves to incorporate more tools for specific needs in assessing clinical reasoning skills. Among these tools, Script Concordance Test (SCT) has a particular importance due to its focus on assessing decision-making in uncertain clinical situations. However, development of SCT items is effortful. Artificial intelligence tools, such as large language models, offer significant benefits. These models are already used for generating multiple-choice questions, and their use in generating SCTs offers great promise. However, this requires well-designed prompts to generate SCTs. This article proposes a generic prompt for the ChatGPT-4, Claude 3, Llama 3, and ChatGPT-4o large language model chatbots to generate SCTs, which can be tailored to various fields of medicine and different stages of medical education. It can help to streamline the development process of SCTs. Initial findings are promising, and there is a need for generating SCTs using large language models and conducting research to assess the quality of SCTs. https://revistas.um.es/edumed/article/view/612381script concordance testclinical reasoningmedical educationartificial intelligenceChatGPTautomatic item generation |
| spellingShingle | Yavuz Selim Kıyak Emre Emekli A Prompt for Generating Script Concordance Test Using ChatGPT, Claude, and Llama Large Language Model Chatbots Revista Española de Educación Médica script concordance test clinical reasoning medical education artificial intelligence ChatGPT automatic item generation |
| title | A Prompt for Generating Script Concordance Test Using ChatGPT, Claude, and Llama Large Language Model Chatbots |
| title_full | A Prompt for Generating Script Concordance Test Using ChatGPT, Claude, and Llama Large Language Model Chatbots |
| title_fullStr | A Prompt for Generating Script Concordance Test Using ChatGPT, Claude, and Llama Large Language Model Chatbots |
| title_full_unstemmed | A Prompt for Generating Script Concordance Test Using ChatGPT, Claude, and Llama Large Language Model Chatbots |
| title_short | A Prompt for Generating Script Concordance Test Using ChatGPT, Claude, and Llama Large Language Model Chatbots |
| title_sort | prompt for generating script concordance test using chatgpt claude and llama large language model chatbots |
| topic | script concordance test clinical reasoning medical education artificial intelligence ChatGPT automatic item generation |
| url | https://revistas.um.es/edumed/article/view/612381 |
| work_keys_str_mv | AT yavuzselimkıyak apromptforgeneratingscriptconcordancetestusingchatgptclaudeandllamalargelanguagemodelchatbots AT emreemekli apromptforgeneratingscriptconcordancetestusingchatgptclaudeandllamalargelanguagemodelchatbots AT yavuzselimkıyak promptforgeneratingscriptconcordancetestusingchatgptclaudeandllamalargelanguagemodelchatbots AT emreemekli promptforgeneratingscriptconcordancetestusingchatgptclaudeandllamalargelanguagemodelchatbots |