child-directed-speech
Filtering by topic child-directed-speech(1)Clear all filters
- PaperarXiv — Language & NLP (cs.CL)31 May 2026
Child-directed speech facilitates production, not comprehension, in BabyLMs
Bastian Bunzeck, Sina Zarrieß
Child-directed speech (CDS) aids language production but not comprehension in BabyLMs. Evaluating models on a frame-completion task reveals that CDS-trained models produce grammatical completions earlier, while web-crawl-trained models excel at comprehension benchmarks. This dissociation suggests comprehension-focused evaluations underestimate the benefits of CDS for production.
Original abstract
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.