发表机构
Sorbonne Université; Sorbonne Center for Artificial Intelligence; CNRS; Sciences, Norms, Democracy; Institute of Intelligent Systems and Robotics（索邦大学; 索邦人工智能中心; 法国国家科学研究中心; 科学、规范与民主研究所; 智能系统与机器人研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文回顾性分析LLMs在婴儿句法学习研究中的应用，通过认识论评估指出BabyLM等方法论假设及发育现实语料库对基准性能影响有限，揭示LLMs与婴儿学习者的计算差异。
AI 中文摘要
大型语言模型（LLMs）越来越多地被用于研究儿童在早期发展阶段如何习得句法。这尤其是BabyLM挑战赛的核心科学目标，该挑战赛是一项社区范围内的努力，旨在开发在发育现实语料库上训练、同时达到人类水平句法性能的模型。在本文中，我们通过对该研究项目中若干研究进行认识论评估，反思了LLMs在婴儿句法学习研究中的应用。我们讨论了数据集如何构建、实现了哪些模型、它们如何被训练以及如何进行句法评估。我们观察到BabyLM及相关研究的方法论中存在显著假设，从而削弱了其理论范围。我们还观察到，使用发育现实语料库对模型在常用基准上的性能影响有限，这表明LLMs与婴儿句法学习者之间存在重要的计算差异。
英文摘要
Large language models (LLMs) have increasingly been used to investigate how children acquire syntax at an early stage of development. This is notably the central scientific goal of the BabyLM challenge, a community-wide effort to develop models that achieve human-level syntactic performance while being trained on developmentally realistic corpora. In this paper, we reflect on the use of LLMs in the study of infant syntax learning by providing an epistemological assessment of several studies from this research program. We discuss how datasets are built, which models are implemented, how they are trained and syntactically evaluated. We observe significant assumptions in the methodology of BabyLM and related studies, thus mitigating their theoretical scope. We additionally observe that using developmentally-realistic corpora have limited effects on models performance on commonly-used benchmarks, which suggest important computational differences between LLMs and the infant syntax learner.
Journal refEMNLP 2026 Main Conference, ACL SIGDAT, Oct 2026, Budapest (Hungary), Hungary
