Citation notice #4607 · 2026-07-11 03:19:08.018010+00:00

CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification

cites Large lan- guage models encode clinical knowledge,, which carries a correction notice dated 2023-07-27. One-hop deterministic notice: the citation edge exists in the Pith bibliography graph; no model judged whether the citation was load-bearing.

This is not a judgment on the citing paper.

Citing paper Event page Original DOI Notice DOI File a formal challenge All reference changes

01Evidence

Raw extraction · citation context · bibliography index 3

Large language models (LLMs) have demonstrated strong potential across medical applications, particularly in clinical documentation tasks such as discharge summary generation, diagnostic as- sistance, and radiology report generation [1][2]. Landmark models including Med-PaLM and Med- PaLM 2 achieved 67.6% and 86.5% accuracy on USMLE-style questions in the MedQA benchmark, respectively [3][4], while GPT-4 demonstrated competitive performance on the MultiMedQA bench- mark [5]. Among clinical documentation tasks, discharge summary generation is of particular safety significance: discharge summaries serve as the primary record guiding post-discharge medication, follow-up care, and inter-provider communication, and errors introduced at this stage propagate

02Event

Type

Correction

Source

Crossref

Original DOI

10.1038/s41586-023-06291-2

Notice DOI

10.1038/s41586-023-06455-0

Date

2023-07-27

Title

Publisher Correction: Large language models encode clinical knowledge

Reasons

['Correction']

Work

Large lan- guage models encode clinical knowledge, (2023) Nature

Schema constants (for re-runners): correction · crossref

03Dispute this notice

If this citation does not depend on the flagged claim, or the event is wrong, say so. Disputes are public. For a signed challenge against the paper itself, use the formal challenge form.