L2D-Clinical improves F1 by 1.7 points on ADE detection and 9.3 points on MIMIC treatment classification by deferring 7-17% of cases from BERT to LLM.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
L2D-Clinical: Learning to Defer for Adaptive Model Selection in Clinical Text Classification
L2D-Clinical improves F1 by 1.7 points on ADE detection and 9.3 points on MIMIC treatment classification by deferring 7-17% of cases from BERT to LLM.