Fine-tuned 1.2B Japanese medical SLM tops 6 of 8 JMED-LLM tasks against larger models, but the comparison is confounded by benchmark-specific fine-tuning.
Improving language understanding by generative pre-training, 2018
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Technical Report: Small Language Model for Japanese Clinical and Medicine
Fine-tuned 1.2B Japanese medical SLM tops 6 of 8 JMED-LLM tasks against larger models, but the comparison is confounded by benchmark-specific fine-tuning.