From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition

ACL ARR 2025 May Submission1258 Authors

Abstract: We examine the capabilities of language models (LMs) from the critical perspective of human language acquisition. Building on classical language development theories, we propose a three-stage framework to assess the abilities of LMs, ranging from preliminary word understanding to complex grammar and complex logical reasoning. Using this framework, we evaluate the generative capacities of LMs using methods from linguistic research. Results indicate that although recent LMs generally outperform earlier models in overall performance, with some variations due to factors such as model architecture and training objectives, their developmental trajectory does not strictly follow the path of human language acquisition. Models show robust improvement in basic and intermediate tasks during pretraining, yet advanced tasks yield minimal gains, highlighting persistent challenges in higher-order linguistic processing. Notably, in generation tasks, experiments show that linguistic features in the training data shape model performance through context-dependent dimensions analogous to those observed in human language.

Paper Type: Long

Research Area: Linguistic theories, Cognitive Modeling and Psycholinguistics

Research Area Keywords: linguistic theories, computational psycholinguistics, interpretability and analysis of models for NLP

Contribution Types: Model analysis & interpretability, Data resources, Data analysis

Languages Studied: English

Submission Number: 1258