# BabyLM's First Constructions: Causal probing provides a signal of learning

arXiv: https://arxiv.org/abs/2506.02147 · HTML: https://mlsanity.com/paper/2506.02147/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 61 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/1808.09031/) (2018)
- [CausaLM: Causal Model Explanation Through Counterfactual Language Models](https://mlsanity.com/paper/2005.13407/) (2020)
- [Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT](https://mlsanity.com/paper/2004.14786/) (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)
- [Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2504.08165/) (2025)
- [Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs](https://mlsanity.com/paper/2403.19827/) (2024)
- [Cross-Linguistic Syntactic Evaluation of Word Prediction Models](https://mlsanity.com/paper/2005.00187/) (2020)
- [Language models align with human judgments on key grammatical constructions](https://mlsanity.com/paper/2402.01676/) (2024)
- [Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2412.05149/) (2024)
- [Trained on 100 million words and still in shape: BERT meets British National Corpus](https://mlsanity.com/paper/2303.09859/) (2023)
- [The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative](https://mlsanity.com/paper/2210.13181/) (2022)
- [GPT or BERT: why not both?](https://mlsanity.com/paper/2410.24159/) (2024)
- [Quantity doesn't buy quality syntax with neural language models](https://mlsanity.com/paper/1909.00111/) (2019)
- [Is Child-Directed Speech Effective Training Data for Language Models?](https://mlsanity.com/paper/2408.03617/) (2024)
- [Language Models as Models of Language](https://mlsanity.com/paper/2408.07144/) (2024)
- [BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop](https://mlsanity.com/paper/2502.10645/) (2025)
- [Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons](https://mlsanity.com/paper/2403.17760/) (2024)
- [Manipulating language models' training data to study syntactic constraint learning: the case of English passivization](https://mlsanity.com/paper/2407.04593/) (2024)
- [Do Construction Distributions Shape Formal Language Learning In German BabyLMs?](https://mlsanity.com/paper/2503.11593/) (2025)
- [Linguistic Dependencies and Statistical Dependence](https://mlsanity.com/paper/2104.08685/) (2021)
- [Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs](https://mlsanity.com/paper/2502.13195/) (2025)
- [Constructions are Revealed in Word Distributions](https://mlsanity.com/paper/2503.06048/) (2025)
- [Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena](https://mlsanity.com/paper/2403.06965/) (2024)
- [BERTtime Stories: Investigating the Role of Synthetic Story Data in Language Pre-training](https://mlsanity.com/paper/2410.15365/) (2024)

## Abstract (arXiv)

Construction grammar posits that language learners acquire constructions (form-meaning pairings) from the statistics of their environment. Recent work supports this hypothesis by showing sensitivity to constructions in pretrained language models (PLMs), including one recent study (Rozner et al., 2025) demonstrating that constructions shape RoBERTa's output distribution. However, models under study have generally been trained on developmentally implausible amounts of data, casting doubt on their relevance to human language learning. Here we use Rozner et al.'s methods to evaluate construction learning in masked language models from the 2024 BabyLM Challenge. Our results show that even when trained on developmentally plausible quantities of data, models learn diverse constructions, even hard cases that are superficially indistinguishable. We further find correlational evidence that constructional performance may be functionally relevant: models that better represent construction perform better on the BabyLM benchmarks.