In several languages, omitting a verb phrase (VP) in double centre-embedded
structures creates a grammaticality illusion. Similar illusion also exhibited
in Mandarin missing-NP double centre-embedded structures. However, there is no
consensus on its very nature. Instead of treating it as grammaticality
illusion, we argue that ambiguous interpretations of verbs can best account for
this phenomenon in Mandarin. To further support this hypothesis, we conducted
two electroencephalography (EEG) experiments on quasi double centre-embedded
structures whose complexity is reduced by placing the self-embedding relative
clauses into the sentence's subject position. Experiment 1 showed that similar
phenomenon even exhibited in this structure, evidenced by an absence of P600
effect and a presence of N400 effect. In Experiment 2, providing semantic cues
to reduce ambiguity dispelled this illusion, as evidenced by a P600 effect. We
interpret the results under garden-path theory and propose that word-order
difference may account for this cross-linguistic variation.

在中心嵌入结构中，省略动词短语（VP）会产生一种语法上的错觉，而在中文的缺失 NP 中心嵌入结构中也表现出类似的错觉。然而，对其本质并没有共识。我们认为，将动词的不确定解释视为最好解释这种现象的方式，而非将其视为语法上的错觉。为了进一步支持这一假设，我们在准中心嵌入结构上进行了两个脑电图（EEG）实验，通过将自我嵌入的关系从句放置在句子的主语位置来减少复杂性。实验 1 表明，即使在这种结构中也存在类似的现象，证据是缺乏 P600 效应和存在 N400 效应。在实验 2 中，通过提供语义线索来减少歧义性，消除了这种错觉，证据是存在 P600 效应。我们根据园路理论解释了这些结果，并提出了词序差异可能解释这种跨语言变异。

语法正确性幻觉还是模棱两可的解释？事件相关电位揭示了汉语中心嵌套结构中缺失 NP 效应的本质

Grammaticality illusion or ambiguous interpretation? Event-related  potentials reveal the nature of the missing-NP effect in Mandarin  centre-embedded structures

A growing body of literature has focused on detailing the linguistic
knowledge embedded in large, pretrained language models. Existing work has
shown that non-linguistic biases in models can drive model behavior away from
linguistic generalizations. We hypothesized that competing linguistic processes
within a language, rather than just non-linguistic model biases, could obscure
underlying linguistic knowledge. We tested this claim by exploring a single
phenomenon in four languages: English, Chinese, Spanish, and Italian. While
human behavior has been found to be similar across languages, we find
cross-linguistic variation in model behavior. We show that competing processes
in a language act as constraints on model behavior and demonstrate that
targeted fine-tuning can re-weight the learned constraints, uncovering
otherwise dormant linguistic knowledge in models. Our results suggest that
models need to learn both the linguistic constraints in a language and their
relative ranking, with mismatches in either producing non-human-like behavior.

本文研究了大型预训练语言模型中内嵌的语言知识，并探索了同时存在的竞争性语言过程如何影响模型行为。通过对四种语言中的一个现象进行实验，发现模型行为存在跨语言差异。而有针对性的微调可以重新建立学习的约束，揭示模型中否则未表现出的语言知识。