# Child-directed speech facilitates production, not comprehension, in BabyLMs

arXiv: https://arxiv.org/abs/2606.01045 · HTML: https://mlsanity.com/paper/2606.01045/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 81 references that are in the map.
- First posted on arXiv 31 May 2026.

## Builds on (most cited first, 28 of 28)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model](https://mlsanity.com/paper/2502.02737/) (2025)
- [Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://mlsanity.com/paper/2512.20848/) (2025)
- [CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists](https://mlsanity.com/paper/2403.18771/) (2024)
- [Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2504.08165/) (2025)
- [MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2504.02768/) (2025)
- [Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2412.05149/) (2024)
- [The Impact of Depth on Compositional Generalization in Transformer Language Models](https://mlsanity.com/paper/2310.19956/) (2023)
- [How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases](https://mlsanity.com/paper/2305.19905/) (2023)
- [How Do LLMs Use Their Depth?](https://mlsanity.com/paper/2510.18871/) (2025)
- [Evaluating Neural Language Models as Cognitive Models of Language Acquisition](https://mlsanity.com/paper/2310.20093/) (2023)
- [Do Construction Distributions Shape Formal Language Learning In German BabyLMs?](https://mlsanity.com/paper/2503.11593/) (2025)
- [Dialogue Is Not Enough to Make a Communicative BabyLM (But Neither Is Developmentally Inspired Reinforcement Learning)](https://mlsanity.com/paper/2510.20358/) (2025)
- [Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale](https://mlsanity.com/paper/2305.17266/) (2023)
- [Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs](https://mlsanity.com/paper/2502.13195/) (2025)
- [BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data](https://mlsanity.com/paper/2510.10159/) (2025)
- [Recurrent babbling: evaluating the acquisition of grammar from limited input data](https://mlsanity.com/paper/2010.04637/) (2020)
- [Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models](https://mlsanity.com/paper/2505.23689/) (2025)
- [A systematic investigation of learnability from single child linguistic input](https://mlsanity.com/paper/2402.07899/) (2024)
- [Emergent Abilities in Reduced-Scale Generative Language Models](https://mlsanity.com/paper/2404.02204/) (2024)
- [Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluations](https://mlsanity.com/paper/2506.16678/) (2025)
- [Constructions are Revealed in Word Distributions](https://mlsanity.com/paper/2503.06048/) (2025)
- [Domain Regeneration: How well do LLMs match syntactic properties of text domains?](https://mlsanity.com/paper/2505.07784/) (2025)
- [Automatic Annotation of Grammaticality in Child-Caregiver Conversations](https://mlsanity.com/paper/2403.14208/) (2024)
- [What Should Baby Models Read? Exploring Sample-Efficient Data Composition on Model Performance](https://mlsanity.com/paper/2411.06672/) (2024)
- [A Distributional Perspective on Word Learning in Neural Language Models](https://mlsanity.com/paper/2502.05892/) (2025)

## Abstract (arXiv)

Recent studies suggest that child-directed speech is not conducive to language learning in BabyLMs. However, current evaluations focus predominantly on comprehension and not production, which is central to usage-based theories of language acquisition which argue how CDS facilitates early language use through constructional ''frames'' (frequent lexical patterns with open slots). We introduce a novel generation-based evaluation inspired by such theories in form of a frame-completion task, and compare Llama models trained with CDS, the BabyLM corpus, and web-crawl data (FineWeb-edu) on comprehension benchmarks and our novel framework. Our results reveal a clear dissociation between models' comprehension and production capabilities: while FineWeb-trained models excel at minimal pairs, CDS-trained models produce grammatical completions substantially earlier in training and concentrate probability mass on appropriate slot-fillers. These findings show that comprehension benchmarks underestimate what CDS affords to BabyLMs.