Evaluating Web Retrieval-Assisted Large Language Models With and Without Whitelisting for Evidence-Based Neurology: Comparative Study.

ABSTRACT:

Background

Large language models (LLMs) coupled with real-time web retrieval are reshaping how clinicians and patients locate medical evidence, and as major search providers fuse LLMs into their interfaces, this hybrid approach might become the new "gateway" to the internet. However, open-web retrieval exposes models to nonprofessional sources, risking hallucinations and factual errors that might jeopardize evidence-based care.

Objective

We aimed to quantify the impact of guideline-domain whitelisting on the answer quality of 3 publicly available Perplexity web-based retrieval-augmented generation (RAG) models and compare their performance using a purpose-built, biomedical literature RAG system (OpenEvidence).

Methods

We applied a validated 130-item question set deriv

SUBMITTER: Masanneck L 

PROVIDER: S-EPMC12612646 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature