Abstract grammatical knowledge - of parts of speech and grammatical patterns - is key to the capacity for linguistic generalization in humans. But how abstract is grammatical knowledge in large language models? In the human literature, compelling evidence for grammatical abstraction comes from structural priming. A sentence that shares the same grammatical structure as a preceding sentence is processed and produced more readily. Because confounds exist when using stimuli in a single language, evidence of abstraction is even more compelling from crosslingual structural priming, where use of a syntactic structure in one language primes an analogous structure in another language. We measure crosslingual structural priming in large language models, comparing model behavior to human experimental results from eight crosslingual experiments covering six languages, and four monolingual structural priming experiments in three non-English languages. We find evidence for abstract monolingual and crosslingual grammatical representations in the models that function similarly to those found in humans. These results demonstrate that grammatical representations in multilingual language models are not only similar across languages, but they can causally influence text produced in different languages.

翻译：抽象语法知识——包括词类与语法模式——是人类语言泛化能力的关键。然而，大型语言模型中的语法知识究竟有多抽象？在人类研究文献中，语法抽象化的有力证据来自结构启动效应：当句子与前一句子共享相同语法结构时，其加工与产出会更为顺畅。由于单一语言刺激存在混淆因素，跨语言结构启动——即一种语言的句法结构会促进另一种语言中类似结构的使用——提供了更具说服力的抽象化证据。我们通过大型语言模型测量跨语言结构启动效应，将模型行为与涵盖六种语言的八项跨语言人类实验以及三项非英语语言的四项单语结构启动实验结果进行对比。研究发现，模型存在类似人类的抽象单语与跨语言语法表征，其运作机制与人类发现高度相似。这些结果表明，多语言语言模型中的语法表征不仅具有跨语言相似性，更能对跨语言文本生成产生因果性影响。