paperDecember 2025Unreviewed

Toward Trustworthy Chatbots: A Protocol for Red Teaming for Health Related Conversations

Syed-Amad Hussain, Daniel I. Jackson, Ashley Lewis, Eric Fosler-Lussier, Emre Sezgin

medRxiv

Abstract

Introduction: Health-related chatbots are increasingly used to mediate conversations that carry clinical significance and emotional weight. Retrieval-augmented generation (RAG) can reduce factual errors ('hallucinations'), but the risks remain, with additional challenges coming from chatbots acting against behavioral safety and scope rules. Red teaming, an adversarial testing process that deliberately probes systems for failures before deployment, offers a way to surface potential risks. We desc

Framework mappings

NIST AI Risk Management Framework

MEASUREMeasure

Suggested from the entry's categories.

Cite

@article{hussain2025trustworthy,
  title = {{Toward Trustworthy Chatbots: A Protocol for Red Teaming for Health Related Conversations}},
  author = {Syed-Amad Hussain and Daniel I. Jackson and Ashley Lewis and Eric Fosler-Lussier and Emre Sezgin},
  year = {2025},
  month = dec,
  journal = {medRxiv},
  doi = {10.64898/2025.12.15.25342297},
  url = {https://www.semanticscholar.org/paper/930205acf84599560a761027e57b15506d11fe7b}
}