Related Experiment Video
Updated: Jun 12, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Can Large Language Models Serve as Reliable Tools for Information in Dentistry? A Systematic Review
Nora Alhazmi1, Aram Alshehri2, Fahad BaHammam2
1Department of Preventive Dental Sciences, College of Dentistry, King Saud bin Abdulaziz University for Health Sciences, King Abdullah International Medical Research Center, Ministry of the National Guard Health Affairs, Riyadh, Saudi Arabia.
Large language models (LLMs) show promise for dental education, potentially improving student performance. However, their use requires caution due to misinformation risks and unreliable citations.
Area of Science:
- Dental Education
- Artificial Intelligence in Healthcare
- Information Science
Background:
- Large language models (LLMs) are increasingly utilized by dental students for subject-specific information retrieval.
- Widespread adoption of LLMs in dentistry raises significant concerns regarding the potential for misinformation.
- A critical evaluation of LLM performance in dental education is necessary.
Purpose of the Study:
- To systematically review and critically assess studies evaluating the performance of large language models (LLMs) in the field of dentistry.
- To identify the benefits and limitations of LLMs as educational tools for dental students.
- To provide evidence-based recommendations for the ethical and effective integration of LLMs in dental curricula.
Main Methods:
- A comprehensive systematic search was performed across multiple major scientific databases (PubMed/Medline, Scopus, Embase, Web of Science, Google Scholar, Saudi Digital Library) up to September 2024.
- Included studies were assessed for quality using the Prediction Model Risk of Bias Assessment Tool (PROBAST).
- Data extraction and synthesis were conducted on 31 studies that met the inclusion criteria.
Main Results:
- Out of 2030 identified studies, 31 met the inclusion criteria after screening and deduplication.
- Approximately half of the included studies were classified as "high risk" for bias, while the remainder were "low risk."
- Key limitations identified include LLMs' inability to cite sources and their propensity for generating fabricated citations, though applicability was rated as "low concern."
Conclusions:
- Large language models (LLMs) demonstrate potential as supplementary educational tools in dentistry, possibly enhancing academic performance.
- Concerns regarding inaccuracies and unreliable citations necessitate further research and integration with validated resources.
- LLMs should be adopted as complementary tools in dental education, with a strong emphasis on ethical guidelines and awareness of their limitations.
Related Concept Videos
Language and Cognition
Teeth
In the bud stage, the tooth germ (an aggregation of cells) starts to form in the developing jawbone. During the cap stage, the tooth germ differentiates into enamel organ, dental papilla, and dental sac, which will later develop into the tooth's enamel, dentin...
Improving Translational Accuracy

