From Priors to Predictions: Explaining and Visualizing Human Reasoning in a Graph Neural Network Framework
This work provides a principled, interpretable framework for modeling human reasoning, which could aid in developing more human-aligned AI systems, though it is incremental in applying existing graph methods to a specific cognitive domain.
The authors tackled the problem of understanding human inductive biases in reasoning by formalizing them as graph-based priors within a Graph Neural Network framework, showing that differences in these priors explain individual human solution variations on an adapted Abstraction and Reasoning Corpus dataset.
Humans excel at solving novel reasoning problems from minimal exposure, guided by inductive biases, assumptions about which entities and relationships matter. Yet the computational form of these biases and their neural implementation remain poorly understood. We introduce a framework that combines Graph Theory and Graph Neural Networks (GNNs) to formalize inductive biases as explicit, manipulable priors over structure and abstraction. Using a human behavioral dataset adapted from the Abstraction and Reasoning Corpus (ARC), we show that differences in graph-based priors can explain individual differences in human solutions. Our method includes an optimization pipeline that searches over graph configurations, varying edge connectivity and node abstraction, and a visualization approach that identifies the computational graph, the subset of nodes and edges most critical to a model's prediction. Systematic ablation reveals how generalization depends on specific prior structures and internal processing, exposing why human like errors emerge from incorrect or incomplete priors. This work provides a principled, interpretable framework for modeling the representational assumptions and computational dynamics underlying generalization, offering new insights into human reasoning and a foundation for more human aligned AI systems.