# How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech

arXiv: https://arxiv.org/abs/2301.11462 · HTML: https://mlsanity.com/paper/2301.11462/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 70 references that are in the map.
- First posted on arXiv 26 Jan 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [A Systematic Assessment of Syntactic Generalization in Neural Language Models](https://mlsanity.com/paper/2005.03692/) (2020)
- [Open Sesame: Getting Inside BERT's Linguistic Knowledge](https://mlsanity.com/paper/1906.01698/) (2019)
- [How Can We Accelerate Progress Towards Human-like Linguistic Generalization?](https://mlsanity.com/paper/2005.00955/) (2020)
- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [What do RNN Language Models Learn about Filler-Gap Dependencies?](https://mlsanity.com/paper/1809.00042/) (2018)
- [Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks](https://mlsanity.com/paper/2001.03632/) (2020)
- [Visually Grounded Neural Syntax Acquisition](https://mlsanity.com/paper/1906.02890/) (2019)
- [Can neural networks acquire a structural bias from raw linguistic data?](https://mlsanity.com/paper/2007.06761/) (2020)
- [Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks](https://mlsanity.com/paper/1802.09091/) (2018)
- [Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models](https://mlsanity.com/paper/2203.09397/) (2022)
- [Transformers Generalize Linearly](https://mlsanity.com/paper/2109.12036/) (2021)
- [Learning Which Features Matter: RoBERTa Acquires a Preference for Linguistic Generalizations (Eventually)](https://mlsanity.com/paper/2010.05358/) (2020)
- [Recurrent babbling: evaluating the acquisition of grammar from limited input data](https://mlsanity.com/paper/2010.04637/) (2020)
- [Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs](https://mlsanity.com/paper/2005.00019/) (2020)

## Built on by (most cited first, 22 of 22)

- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Modeling rapid language learning by distilling Bayesian priors into artificial neural networks](https://mlsanity.com/paper/2305.14701/) (2023)
- [Re-evaluating Theory of Mind evaluation in large language models](https://mlsanity.com/paper/2502.21098/) (2025)
- [Large Linguistic Models: Investigating LLMs' metalinguistic abilities](https://mlsanity.com/paper/2305.00948/) (2023)
- [Large Language Models as Proxies for Theories of Human Linguistic Cognition](https://mlsanity.com/paper/2502.07687/) (2025)
- [A systematic framework for generating novel experimental hypotheses from language models](https://mlsanity.com/paper/2408.05086/) (2024)
- [A systematic investigation of learnability from single child linguistic input](https://mlsanity.com/paper/2402.07899/) (2024)
- [Whither symbols in the era of advanced neural networks?](https://mlsanity.com/paper/2508.05776/) (2025)
- [Metacognitive Sensitivity for Test-Time Dynamic Model Selection](https://mlsanity.com/paper/2512.10451/) (2025)
- [The Quo Vadis of the Relationship between Language and Large Language Models](https://mlsanity.com/paper/2310.11146/) (2023)
- [Bearing Syntactic Fruit with Stack-Augmented Neural Networks](https://mlsanity.com/paper/2511.03547/) (2025)
- [Age-Dependent Analysis and Stochastic Generation of Child-Directed Speech](https://mlsanity.com/paper/2405.07700/) (2024)
- [Language models as tools for investigating the distinction between possible and impossible natural languages](https://mlsanity.com/paper/2512.09394/) (2025)
- [Large language models have learned to use language](https://mlsanity.com/paper/2512.12447/) (2025)
- [Large language models are not about natural language](https://mlsanity.com/paper/2512.13441/) (2025)
- [Linguists should learn to love speech-based deep learning models](https://mlsanity.com/paper/2512.14506/) (2025)
- [Are Language Models Models?](https://mlsanity.com/paper/2601.10421/) (2026)
- [Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities](https://mlsanity.com/paper/2604.09466/) (2026)
- [You Can't Fight in Here! This is BBS!](https://mlsanity.com/paper/2604.09501/) (2026)
- [Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear](https://mlsanity.com/paper/2605.10061/) (2026)
- [Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulations](https://mlsanity.com/paper/2609.06025/) (2026)
- [Co-Linguistics: AI-augmented Theory Construction in Linguistics](https://mlsanity.com/paper/2609.37635/) (2026)

## Abstract (arXiv)

When acquiring syntax, children consistently choose hierarchical rules over competing non-hierarchical possibilities. Is this preference due to a learning bias for hierarchical structure, or due to more general biases that interact with hierarchical cues in children's linguistic input? We explore these possibilities by training LSTMs and Transformers - two types of neural networks without a hierarchical bias - on data similar in quantity and content to children's linguistic input: text from the CHILDES corpus. We then evaluate what these models have learned about English yes/no questions, a phenomenon for which hierarchical structure is crucial. We find that, though they perform well at capturing the surface statistics of child-directed speech (as measured by perplexity), both model types generalize in a way more consistent with an incorrect linear rule than the correct hierarchical rule. These results suggest that human-like generalization from text alone requires stronger biases than the general sequence-processing biases of standard neural network architectures.