Tag
该论文利用 Pythia 和 OLMo 等开源模型的中间检查点，系统研究了大语言模型在训练过程中形态结构、嵌入漂移、重复主导与共现效应的演化规律，发现模型在语义嵌入稳定之前就已习得形态结构，且训练数据规模有助于发散识别，而共现和重复则有负面影响。
This paper introduces a method using GPT-2 token surprisal to label telicity in child language, finding that child models rely on syntactic cues like post-verbal determiners, while adult models use semantic features, supporting syntactic bootstrapping theory.
This paper proposes collocational bootstrapping, a mechanism by which statistical word co-occurrence cues can aid the acquisition of English subject-verb agreement, supported by neural network simulations and analysis of child-directed speech.
This paper proposes LAD-inspired pre-pretraining using a formal language called MP-Struct that encodes natural-language-like structures. It shows that this approach improves token efficiency and imparts human-like resistance to structurally implausible languages, challenging prior hypotheses about effective pre-pretraining languages.
This paper presents a computational approach using large language models and RoBERTa to identify manner and result verbs in sentence context, achieving up to 89.6% accuracy. It aims to provide a scalable measurement tool for developmental language research.
This paper presents a computational framework to test competing maturational theories of syntactic development in children, specifically comparing bottom-up versus inward accounts using statistical grammar induction.