medRxiv PreprintsInternational16 November 2026
Prompt Injection Can Alter Large Language Model Scores and Feedback on Medical Student Essays: A Four-Model Stress Test
This is an official announcement record
Firsthand records what medRxiv Preprints announced and links to the original. The wording below is theirs, not ours.
Background: Large language models (LLMs) can support health professions educational assessment by scoring narrative text. However, educator-authored scoring instructions and student text enter the same language-processing context. Prompt injection exploits this boundary by embedding LLM-directed instructions ("attacks") within to-be-assessed text. The scope of this problem across different LLM configurations, attack conditions, and attacker objectives remains incompletely characterized. This study explores: How susceptible is LLM scoring to various prompt injection attacks embedded in reflecti
Read the official announcement
Opens www.medrxiv.org
More from medRxiv Preprints
- Unmet needs of Polish patients with cystic fibrosis seen through the lens of crowdfunding20 November 2026
- Motherly Plus: Study Protocol of a Randomized Controlled Trial Evaluating a Smartphone-Assisted Single-Session Psychotherapy Intervention for Postpartum Depression20 November 2026
- Targeting memory consolidation in major depression via pharmacological slow-wave sleep promotion20 November 2026
- Epidemiology of Cardiac Structure and Function Among African Caribbeans in Tobago: A Population-based Cohort Study20 November 2026
- Depressive Symptom Trajectories and Incident Cognitive Impairment by Outcome Ascertainment20 November 2026
This content is for informational purposes only and is not medical advice. It is not intended to diagnose, treat, cure, or prevent any disease. Consult a healthcare professional before starting any supplement, treatment, or program: especially if you are pregnant, nursing, taking medication, or managing a health condition.