AI models are often developed to solve reasoning problems op-
timally. In contrast, cognitive models focus on explaining and
predicting replicative cognitive patterns of human information
processing. And while many of the theories aim to explain
an assumed ‘general’ human reasoner, only few are aimed at
the individual. This paper addresses the challenge of the lat-
ter by investigating the automatic generation of individualised
predictive algorithms using transformer-based models. These
models which have been trained on huge amounts of human
data, potentially exhibit built-in cognitive patterns. Leverag-
ing such characteristics and architecture of transformer-based
models, we outline a generalized methodology for establishing
a human-AI collaborative framework, to generate explainable
and reproducible algorithms with cross-domain applicability.
While predictive accuracy and generalizability pose less of a
problem, the bigger challenges in using machine learning ap-
proaches or transformer-based models may be explainability
and replicability. Hence, instead of ‘just’ using such a model
for directly fitting the data, we use it to extract features and
to propose cognitive algorithms that are executable in systems
outside of the model. Using two datasets pertaining to syl-
logistic and spatial reasoning, the predictive algorithms thus
generated applying the presented framework, achieve mean ac-
curacies of 68% and 81%, respectively. Both algorithms out-
perform other established, state-of-the-art cognitive models by
far, surpassing the (previously) best state-of-the art models in
syllogistic and spatial human reasoning by 19% and 13%, re-
spectively.