Lightweight LLMs lose 7.2 percentage points of accuracy when false health claims are injected into prompts, but only 1.4 points when medical jargon is replaced with everyday language.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating LLM Robustness Under Domain-Specific Prompt Perturbations in Public Health Applications
Lightweight LLMs lose 7.2 percentage points of accuracy when false health claims are injected into prompts, but only 1.4 points when medical jargon is replaced with everyday language.