One Model, Two Minds: A Context-Gated Graph Learner that Recreates Human Biases
This work addresses the challenge of creating AI systems with human-like social cognition and adaptive decision-making, bridging artificial intelligence and cognitive theory, though it is incremental in combining existing methods.
The paper tackled the problem of replicating human cognitive biases in AI by introducing a dual-process model that integrates fast graph-based reasoning and slow meta-adaptive learning, achieving results that closely mirror human adaptive behavior and generalize to unseen contexts.
We introduce a novel Theory of Mind (ToM) framework inspired by dual-process theories from cognitive science, integrating a fast, habitual graph-based reasoning system (System 1), implemented via graph convolutional networks (GCNs), and a slower, context-sensitive meta-adaptive learning system (System 2), driven by meta-learning techniques. Our model dynamically balances intuitive and deliberative reasoning through a learned context gate mechanism. We validate our architecture on canonical false-belief tasks and systematically explore its capacity to replicate hallmark cognitive biases associated with dual-process theory, including anchoring, cognitive-load fatigue, framing effects, and priming effects. Experimental results demonstrate that our dual-process approach closely mirrors human adaptive behavior, achieves robust generalization to unseen contexts, and elucidates cognitive mechanisms underlying reasoning biases. This work bridges artificial intelligence and cognitive theory, paving the way for AI systems exhibiting nuanced, human-like social cognition and adaptive decision-making capabilities.