Related Experiment Video
Updated: May 20, 2025
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Large language model-supported interactive case-based learning: a pilot study.
Haelynn Gim1, Benjamin Cook2, Jasmin Le2
1Harvard Medical School, Boston, Massachusetts, USA.
Large language models (LLMs) show promise for case-based learning, with a new tool adhering to medical screenplays in 97.1% of cases. Further research is needed to confirm their educational impact.
Area of Science:
- Medical Education
- Artificial Intelligence
Background:
- Large language models (LLMs) offer potential for enhancing case-based learning.
- A key challenge is LLMs' tendency to generate factually incorrect information.
Purpose of the Study:
- To develop and evaluate an LLM-based tool for augmenting case-based learning.
- To assess the factual accuracy and medical appropriateness of LLM responses.
Main Methods:
- An LLM-based tool was developed for case-based learning.
- The tool's performance was evaluated based on adherence to a provided screenplay.
- Medical appropriateness of responses was also assessed.
Main Results:
- The LLM adhered to the provided screenplay in 97.1% (832/857) of instances.
- In remaining instances, responses were medically appropriate in 96.0% (24/25) of cases.
Conclusions:
- LLM use appears feasible for augmenting case-based learning.
- Further studies are necessary to determine the educational impact of LLMs in this context.
More Related Videos
13:44Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques
Published on: December 9, 2022
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
