Watermarking medical AI outputs can degrade reasoning, terminology, and image interpretation even when benchmark accuracy stays stable, so accuracy-only evaluations hide clinically important damage.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Marking the Wrong Symptoms: Evaluating LLM Watermarks in Medical Texts
Watermarking medical AI outputs can degrade reasoning, terminology, and image interpretation even when benchmark accuracy stays stable, so accuracy-only evaluations hide clinically important damage.