Sign inGet started
Paper · arXiv

Audit Before You Distill: A Controlled Workflow for Reasoning Transfer into Compact Medical Language Models

Teacher rationales can help a smaller model answer health professions questions, but they can also reinforce errors. We examined when they help and how this evidence can guide training using Brazilian Portuguese questions from medical and multiprofessional residency examinations. First, we measured how a teacher rationale changed the student's probability of selecting the correct answer and compared this effect with rationales drawn from other questions. The complete rationale increased this probability by 21~p.p. when the teacher was correct and decreased it by 14~p.p. when the teacher was wrong. By intervening on the reasoning content, we showed that shuffled rationales did not produce ...

AuthorsTiago Martinelli, João Paulo Papa, Adriano José Pereira
Primary categorycs.CL
Published12 October 2026
Last updated at source12 October 2026
cs.CLcs.AI
Embed this entry
<iframe src="https://silytics.si/embed/item/af4cf12c-8903-44b4-afd7-8d84497534b8" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.