Reason2Decide applies staged multi-task learning with scheduled sampling to improve both prediction accuracy and rationale fidelity in clinical tasks using models 40x smaller than foundation models.
If the predicted disposition is Go to L&D now , does the generated ra- tionale justify the decision - nothomecare?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reason2Decide: Rationale-Driven Multi-Task Learning
Reason2Decide applies staged multi-task learning with scheduled sampling to improve both prediction accuracy and rationale fidelity in clinical tasks using models 40x smaller than foundation models.