Publikation
Psychology-Grounded Individualized Artificial Mental Model
Prajvi Saxena; Arvind Nagarajan; Sabine Janzen; Wolfgang Maaß
In: ArtifiAI for Aging Rehabilitation and Intelligent Assisted Living; 9th International Workshop, ARIAL 2026, Held in Conjunction with IJCAI 2026, Proceedings. Workshop on Data Mining for Ageing, Rehabilitation and Independent Assisted Living (ARIAL-2026), 9th International Workshop, ARIAL in conjunction with the 35th International Joint Conference on AI, 2026., located at IJCAI-2026, August 17-21, Bremen, Germany, Springer Communications in Computer and Information Science (CCIS), 8/2026.
Zusammenfassung
Personalizing rehabilitation requires predicting how individual patients will experience pain yet two patients undergoing identical surgery can report starkly different outcomes. This heterogeneity is not noise: it is systematically driven by personality, beliefs, emotional state, and life circumstances. Psychology has spent decades formalizing precisely these individual differences through validated frameworks such as the Biopsychosocial model and the International Classification of Functioning. Yet existing AI approaches ignore this theoretical structure and treating patient variables as flat numerical features. We propose Psychology-Grounded Artificial Mental Models: a framework that encodes established psychological theory as structured reasoning scaffolds within large language models, enabling them to construct an artificial mental model of each patient before making predictions. To evaluate the framework, we conducted a DiscoverYourself study with 336 participants, and further validated the framework on publicly available PhysioPain dataset (N=82). Across four LLM families, theory-grounded models achieve up to +56.9 percentage points exact-accuracy improvement over the generic baseline. These results indicate that encoding psychological theory into LLM reasoning substantially improves pain prediction in rehabilitation, with the largest gains observed among older, highly heterogeneous patients where data-driven models are least reliable.