Framing Bias in a Large Language Model: A Diagnostic Accuracy Study of Prompt Effects on ChatGPT’s Melanoma Classification

Published: 18 November 2025| Version 1 | DOI: 10.17632/tpcf29wdzj.1
Contributors:
,
,
, Ketty Peris

Description

- Mendeley Supplemental Figure 1. Representative examples of the test. Each image was presented six times under different instructions: a neutral baseline prompt, and five framed prompts. - Mendeley Supplemental File 1. Detailed Materials and methods (Study design, Model Access and Interaction, Dataset Details, Prompting Procedure, Outcome Measures and Statistical Analysis) of the study

Files

Institutions

  • Universita Cattolica del Sacro Cuore

Categories

Artificial Intelligence, Dermatology, Melanoma, Large Language Model

Funders

  • None

Additional Metadata for UCSC Datasets

CampusRome
Scientific Disciplinary Area (after 2024)MEDS-10/C - Dermatology and Venereal Diseases

Licence