Evaluating the safety of large language models in healthcare and dentistry: adversarial testing approaches

Abstract

The emergence of large language models (LLMs) provides new avenues for clinical support in healthcare and dentistry. However, these models often exhibit unpredictable behaviours when challenged by adversarial or misleading inputs. Recent data indicate that nearly 20% of LLM outputs contain safety risks or biases, necessitating rigorous evaluation prior to clinical use. This review examines AI red teaming, a systematic approach for identifying system vulnerabilities through simulated attacks. It

Categories

Framework mappings

Suggested from the entry's categories.

@article{umer2026evaluating,
  title = {{Evaluating the safety of large language models in healthcare and dentistry: adversarial testing approaches}},
  author = {F. Umer and Muhammad Muthar Shaikh and Absar Ur Rahman},
  year = {2026},
  month = jul,
  journal = {BDJ Open},
  doi = {10.1038/s41405-026-00462-9},
  url = {https://www.semanticscholar.org/paper/1701841a90c671a0ac638bf3e721d010046a6488}
}