MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models

Excerpt

arXiv:2609.38543v1 Announce Type: cross Abstract: Constantly evolving real-world knowledge necessitates models to be updated continuously. Especially in medicine, as clinical evidence changes over time, outdated knowledge can pose safety risks. Existing evaluations of knowledge integration focus on factual recall, offering limited insight into whether newly integrated knowledge is actually usable. Our benchmark MedKIT (Medical Knowledge Integration and Transfer) provides a granular evaluation of