mlsanityData to 7 Oct 2026

Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition

arXiv 2502.04795 ↗First posted 7 Feb 2025cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Large language models possess general linguistic abilities but acquire language less efficiently than humans. This study proposes a method for integrating the developmental characteristics of working memory during the critical period, a stage when human language acquisition is particularly efficient, into the training process of language models. The proposed method introduces a mechanism that initially constrains working memory during the early stages of training and gradually relaxes this constraint in an exponential manner as learning progresses. Targeted syntactic evaluation shows that the proposed method outperforms conventional methods without memory constraints or with static memory constraints. These findings not only provide new directions for designing data-efficient language models but also offer indirect evidence supporting the role of the developmental characteristics of working memory as the underlying mechanism of the critical period in language acquisition.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 16 of its 56 references that are in the map. First posted on arXiv 7 Feb 2025.

Builds on

16 of 56 references.

References · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,085
  7. 2019BLiMP: The Benchmark of Linguistic Minimal Pairs for Englishcited by 553
  8. 2018Colorless green recurrent networks dream hierarchicallycited by 210
  9. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  10. 2020Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networkscited by 72
  11. 2016Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learnercited by 68
  12. 2025How Linguistics Learned to Stop Worrying and Love the Language Modelscited by 50
4 more
  1. 2021CLiMP: A Benchmark for Chinese Language Model Evaluationcited by 44
  2. 2024Is Child-Directed Speech Effective Training Data for Language Models?cited by 24
  3. 2024Linear Recency Bias During Training Improves Transformers' Fit to Reading Timescited by 14
  4. 2024Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 6.

10 papers.