Challenges of GPT-3-based Conversational Agents for Healthcare

0Citations
Citations of this article
26Readers
Mendeley users who have this article in their library.

Abstract

The potential to provide patients with faster information access while allowing medical specialists to concentrate on critical tasks makes medical domain dialog agents appealing. However, the integration of large-language models (LLMs) into these agents presents certain limitations that may result in serious consequences. This paper investigates the challenges and risks of using GPT-3-based models for medical question-answering (MedQA). We perform several evaluations contextualized in terms of standard medical principles. We provide a procedure for manually designing patient queries to stress-test high-risk limitations of LLMs in MedQA systems. Our analysis reveals that LLMs fail to respond adequately to these queries, generating erroneous medical information, unsafe recommendations, and content that may be considered offensive.

Cite

CITATION STYLE

APA

Lechner, F., Lahnala, A., Welch, C., & Flek, L. (2023). Challenges of GPT-3-based Conversational Agents for Healthcare. In International Conference Recent Advances in Natural Language Processing, RANLP (pp. 619–630). Incoma Ltd. https://doi.org/10.26615/978-954-452-092-2_067

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free