2 papers
cs.CL2026
Surrogate modeling for interpreting black-box LLMs in medical predictions
Changho Han, Songsoo Kim, Dong Won Kim +4
Large language models (LLMs), trained on vast datasets, encode extensive real-world knowledge within their parameters, yet their black-box nature obscures the mechanisms and extent…
cs.CL2026
A Dataset and Resources for Identifying Patient Health Literacy Information from Clinical Notes
Madeline Bittner, Dina Demner-Fushman, Yasmeen Shabazz +6
Health literacy is a critical determinant of patient outcomes, yet current screening tools are not always feasible and differ considerably in the number of items, question format,…