The frequency of clinical jargon in pretraining corpora predicts how well open-source LLMs interpret that jargon, but hospital notes use abbreviations that appear only rarely online.
Medical large language models are vulnerable to data-poisoning attacks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Diagnosing our datasets: How does my language model learn clinical information?
The frequency of clinical jargon in pretraining corpora predicts how well open-source LLMs interpret that jargon, but hospital notes use abbreviations that appear only rarely online.