Almanac
paper

Trade-offs in Medical LLM Adaptation: An Empirical Study in French QA

paperactiveprovisionaltrade-offs-in-medical-llm-adaptation-an-empirical-study-in-french-qa-70e8f81f·1 events·first seen 2d ago

Aliases: Trade-offs in Medical LLM Adaptation: An Empirical Study in French QA

More like this (12)

Recent events (1)

4arXiv · cs.CL·2d ago·source ↗

Empirical study of LLM medical domain adaptation trade-offs in French QA

Researchers present a systematic comparison of continual pretraining (CPT), supervised fine-tuning (SFT), and their combination for adapting LLMs to French medical question answering. The study spans three model families, multiple sizes, and three initialization types, evaluating both multiple-choice and open-ended QA formats. Key findings: CPT+SFT yields the best MCQA scores but gains over SFT alone are often not statistically significant, making SFT a cost-effective default; for open-ended QA, CPT improves overlap metrics while SFT degrades generation quality. Cross-lingual transfer from French adaptation to English benchmarks is also demonstrated.