A neurology NLP project moved from custom model training to RAG with small Gemma models, reporting QA results that are undermined by a contaminated benchmark and internally contradictory claims.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Building Models of Neurological Language
A neurology NLP project moved from custom model training to RAG with small Gemma models, reporting QA results that are undermined by a contaminated benchmark and internally contradictory claims.