Human learning is sensitive to rule-like structure and the curriculum of examples used for training. In tasks governed by succinct rules, learning is more robust when related examples are blocked across trials, but in the absence of such rules, interleaving is more effective. To date, no neural model has simultaneously captured these seemingly contradictory effects. Here we show that this same tradeoff spontaneously emerges with "in-context learning" (ICL) both in neural networks trained with metalearning and in large language models (LLMs). ICL is the ability to learn new tasks "in context" - without weight changes - via an inner-loop algorithm implemented in activation dynamics. Experiments with pretrained LLMs and metalearning transformers show that ICL exhibits the blocking advantage demonstrated in humans on a task involving rule-like structure, and conversely, that concurrent in-weight learning reproduces the interleaving advantage observed in humans on tasks lacking such structure.

翻译：人类学习对规则性结构以及用于训练的示例课程具有敏感性。在受简洁规则支配的任务中，当相关示例跨试验分块呈现时，学习更加稳健；但在缺乏此类规则时，交错呈现则更为有效。迄今为止，尚无神经模型能同时捕捉这些看似矛盾的现象。本文证明，这种权衡会随着"上下文学习"（ICL）在经元学习训练的神经网络及大型语言模型（LLMs）中自发涌现。ICL是指通过激活动力学实现内部循环算法、在无需权重更新的情况下"在上下文中"学习新任务的能力。基于预训练LLMs及元学习Transformer的实验表明，ICL在涉及规则性结构的任务中展现出人类所具备的分块优势；反之，在缺乏此类结构的任务中，并行的权重内学习则复现了人类观察到的交错优势。