A crucial aspect of linguistic capability is the ability to trade off between stored representations and abstract knowledge: one must retrieve learned representations, but also generate novel ones by applying productive rules. While recent work has examined abstract knowledge in language models, holistic storage of multi-word units has received far less attention. We probe internal representations in text-based LLMs and an ASR model, testing whether V+up phrasal verbs develop distinct representations as a function of frequency and predictability. All models show evidence of holistic storage driven by frequency and predictability, further supporting usage-based theories of language.

翻译：语言能力的一个关键方面在于能够在存储表征与抽象知识之间进行权衡：既要检索已习得的表征，也要通过应用能产规则生成新表征。尽管近期研究关注了语言模型中的抽象知识，但对多词单元整体存储的探究却远未充分。我们探究了基于文本的大语言模型和自动语音识别模型中的内部表征，检验V+up短语动词是否因频率和可预测性而形成不同的表征。所有模型均表现出受频率和可预测性驱动的整体存储证据，进一步支持了基于用法的语言理论。