Dementia Language Models: a generalizable and controllable representation of cognitive impairment

Abstract

We introduce Dementia Language Models (DLMs)—a generalizable and controllable representation of cognitive impairment through language—alongside an evaluation framework for establishing their validity and clinical grounding. DLMs created by large language models fine-tuned on a small clinical corpus successfully generated patient-like narratives across unseen tasks, received predicted MMSE scores in the impaired range, and produced narratives that neurologists identified with accuracy comparable to real transcripts. The models’ internal representations themselves, as well as their non-linguistic decision-making, supported cognitive-state detection in unseen cohorts. The effect was controllable: moving from Healthy toward Dementia in weight space progressively worsened language and predicted MMSE scores while increasing dementia probability. DLMs could support clinician training, hypothesis generation, and scalable experimentation, reserving patient involvement for where it is truly needed.