用双系统模型模拟人类思维偏差，让AI更像人一样思考。
One Model, Two Minds: A Context-Gated Graph Learner that Recreates Human Biases
- 设计双系统：快速直觉与慢速反思并行，通过上下文门控动态切换。
- 在错误信念任务中复现锚定、框架效应等认知偏差，表现接近人类。
- 适合研究人类认知机制或开发具社会智能的AI系统。
我们提出一种受认知科学双过程理论启发的意向理论（ToM）新框架，融合基于图卷积网络（GCNs）的快速习惯性推理系统（系统1）和基于元学习的缓慢情境敏感元自适应学习系统（系统2）。模型通过可学习的上下文门控机制动态平衡直觉与深思熟虑的推理。我们在经典错误信念任务上验证该架构，并系统探究其复现双过程理论典型认知偏差的能力，包括锚定效应、认知负荷疲劳、框架效应和启动效应。实验结果表明，该双系统方法能高度贴近人类适应性行为，在未见情境下实现稳健泛化，并揭示推理偏差背后的认知机制。本工作连接人工智能与认知理论，为具备细腻人类社交认知与自适应决策能力的AI系统开辟路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。