Human learning embodies a striking duality: sometimes, we appear capable of following logical, compositional rules and benefit from structured curricula (e.g., in formal education), while other times, we rely on an incremental approach or trial-and-error, learning better from curricula that are unstructured or randomly interleaved. Influential psychological theories explain this seemingly disparate behavioral evidence by positing two qualitatively different learning systems -- one for rapid, rule-based inferences and another for slow, incremental adaptation. It remains unclear how to reconcile such theories with neural networks, which learn via incremental weight updates and are thus a natural model for the latter type of learning, but are not obviously compatible with the former. However, recent evidence suggests that both metalearning neural networks and large language models are capable of "in-context learning" (ICL) -- the ability to flexibly grasp the structure of a new task from a few examples given at inference time. Here, we show that networks capable of ICL can reproduce human-like learning and compositional behavior on rule-governed tasks, while at the same time replicating human behavioral phenomena in tasks lacking rule-like structure via their usual in-weight learning (IWL). Our work shows how emergent ICL can equip neural networks with fundamentally different learning properties than those traditionally attributed to them, and that these can coexist with the properties of their native IWL, thus offering a novel perspective on dual-process theories and human cognitive flexibility.

翻译：人类学习呈现出一种显著的双重性：有时我们似乎能够遵循逻辑性、组合性的规则，并从结构化课程中获益（例如在正规教育中）；而其他时候，我们则依赖于渐进式方法或试错学习，在非结构化或随机穿插的课程中反而学得更好。有影响力的心理学理论通过假设两种性质不同的学习系统来解释这种看似矛盾的行为证据——一个用于快速、基于规则的推理，另一个用于缓慢、渐进的适应。目前尚不清楚如何将这些理论与神经网络相协调：神经网络通过渐进式的权重更新进行学习，因此自然成为后一种学习类型的模型，但显然与前者不相容。然而，近期证据表明，元学习神经网络和大型语言模型均具备"情境学习"能力——即能够在推理时通过少量示例灵活掌握新任务的结构。本文证明，具备情境学习能力的网络能够在规则主导的任务中复现类人的学习与组合行为，同时通过其固有的权重内学习机制，在缺乏规则结构的任务中复现人类行为现象。我们的研究表明，涌现的情境学习能力能够赋予神经网络与传统认知截然不同的学习特性，这些特性可与网络固有的权重内学习特性共存，从而为双过程理论和人类认知灵活性提供了新的视角。