# A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models

arXiv: https://arxiv.org/abs/2602.09992 · HTML: https://mlsanity.com/paper/2602.09992/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 110 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 26 of 26)

- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [A Systematic Assessment of Syntactic Generalization in Neural Language Models](https://mlsanity.com/paper/2005.03692/) (2020)
- [When Do You Need Billions of Words of Pretraining Data?](https://mlsanity.com/paper/2011.04946/) (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)
- [Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs](https://mlsanity.com/paper/2403.19827/) (2024)
- [minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models](https://mlsanity.com/paper/2203.13112/) (2022)
- [Grokking of Hierarchical Structure in Vanilla Transformers](https://mlsanity.com/paper/2305.18741/) (2023)
- [Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale](https://mlsanity.com/paper/2203.00633/) (2022)
- [Language acquisition: do children and language models follow similar learning stages?](https://mlsanity.com/paper/2306.03586/) (2023)
- [Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases](https://mlsanity.com/paper/2502.19249/) (2025)
- [Injecting structural hints: Using language models to study inductive biases in language learning](https://mlsanity.com/paper/2304.13060/) (2023)
- [Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence](https://mlsanity.com/paper/2405.15750/) (2024)
- [Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks](https://mlsanity.com/paper/1802.09091/) (2018)
- [Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers](https://mlsanity.com/paper/2404.16367/) (2024)
- [Is Child-Directed Speech Effective Training Data for Language Models?](https://mlsanity.com/paper/2408.03617/) (2024)
- [BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop](https://mlsanity.com/paper/2502.10645/) (2025)
- [Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models](https://mlsanity.com/paper/2503.20850/) (2025)
- [PaLM: A Hybrid Parser and Language Model](https://mlsanity.com/paper/1909.02134/) (2019)
- [Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition](https://mlsanity.com/paper/2502.04795/) (2025)
- [BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data](https://mlsanity.com/paper/2510.10159/) (2025)
- [Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models](https://mlsanity.com/paper/2505.23689/) (2025)
- [Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision](https://mlsanity.com/paper/2402.12691/) (2024)

## Built on by (most cited first, 1 of 1)

- [Linear representations of grammaticality in neural language models](https://mlsanity.com/paper/2607.15175/) (2026)

## Abstract (arXiv)

Several recent contributions have evaluated the Poverty of the Stimulus Hypothesis (PoSH) using Artificial Neural Networks (ANNs). The results suggest that ANN-based language models can acquire certain structure-dependent generalizations from limited input without structural inductive biases of the type traditionally hypothesized by linguists. However, existing studies have largely focused on individual phenomena and adopted different evaluation protocols, leaving it unclear whether previous findings generalize across phenomena and learning conditions. We introduce poshbench, a unified benchmark covering four canonical PoS phenomena. Training Transformer, LSTM, and n-gram models, we find that ANN-based models can achieve above-chance generalization from surprisingly limited input (10M words), but they show less efficient learning than children as input scale grows. Moreover, cognitively motivated inductive biases substantially improve broad syntactic competence but do not consistently translate to PoS-relevant generalization. Our findings provide systematic evidence challenging the claim that innate syntax is the only possible route to generalization, while suggesting that human-like learning efficiency requires inductive biases beyond those implemented here.