Combining continued pretraining with reasoning preference optimization yields a 72B Japanese medical model that keeps 0.868 accuracy on IgakuQA with and without explanation prompting, while a model without RPO drops to 0.834.
Beyond fine-tuning: Unleashing the potential of continuous pretraining for clinical LLM s
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
-
Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization
Combining continued pretraining with reasoning preference optimization yields a 72B Japanese medical model that keeps 0.868 accuracy on IgakuQA with and without explanation prompting, while a model without RPO drops to 0.834.