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

arXiv: https://arxiv.org/abs/2502.04795 · HTML: https://mlsanity.com/paper/2502.04795/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 56 references that are in the map.
- First posted on arXiv 7 Feb 2025.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks](https://mlsanity.com/paper/2001.03632/) (2020)
- [Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner](https://mlsanity.com/paper/1607.08723/) (2016)
- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [CLiMP: A Benchmark for Chinese Language Model Evaluation](https://mlsanity.com/paper/2101.11131/) (2021)
- [Is Child-Directed Speech Effective Training Data for Language Models?](https://mlsanity.com/paper/2408.03617/) (2024)
- [Linear Recency Bias During Training Improves Transformers' Fit to Reading Times](https://mlsanity.com/paper/2409.11250/) (2024)
- [Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothing](https://mlsanity.com/paper/2410.11462/) (2024)

## Built on by (most cited first, 10 of 10)

- [A Review of Incorporating Psychological Theories in LLMs](https://mlsanity.com/paper/2505.00003/) (2025)
- [Human-like fleeting memory improves language learning but impairs reading time prediction in transformer language models](https://mlsanity.com/paper/2508.05803/) (2025)
- [What is the Best Sequence Length for BABYLM?](https://mlsanity.com/paper/2510.19493/) (2025)
- [A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models](https://mlsanity.com/paper/2602.09992/) (2026)
- [Do Self-Supervised Speech Models Exhibit the Critical Period Effects in Language Acquisition?](https://mlsanity.com/paper/2508.21210/) (2025)
- [CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models](https://mlsanity.com/paper/2602.21978/) (2026)
- [What Kind of Language is Easy to Language-Model Under Curriculum Learning?](https://mlsanity.com/paper/2604.26844/) (2026)
- [Beyond Static and Linear: What Attention Constraints Best Fit Human Reading Times?](https://mlsanity.com/paper/2608.23818/) (2026)
- [Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulations](https://mlsanity.com/paper/2609.06025/) (2026)
- [Typological Alignment of Stack-Based Language Models on Mildly Context-Sensitive Artificial Languages](https://mlsanity.com/paper/2610.02040/) (2026)

## 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.