Child Language Acquisition

Follow this topic Ask about this topic

The field studies how children acquire vocabulary, speech sounds, and grammatical knowledge from caregiver talk, other social interaction, and what they see and hear. Researchers analyze developmental corpora such as CHILDES, measure processing with behavioral tasks and brain responses, and build computational models using statistical learning, BabyLM-scale training, and audiovisual grounding. These approaches test how frequency, syntax, feedback, and interaction shape learning across languages and developmental stages. A central open question is whether models that perform well on language benchmarks capture children's learning mechanisms, given children's efficiency and the importance of grounding and social context.

Latest papers

29 papers3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

Specialization, Diversity, and Scaling in Child-Scale Language Models
Oct 27, 2026Steven Y. Feng, Michael C. FrankSmall Language Models LLM Training
Stanford University
Scaling cross-situational word learning on children's naturalistic experiences
Oct 22, 2026Michael C. Frank, Alvin W. M. Tan, Khai Loong Aw +9Child Language Acquisition Visual Representation Learning
Department of Psychology, Stanford University · Department of Computer Science, Stanford University · Department of Psychology, Harvard University +3
Child-Adapted Structured Phonological Representations for Interpretable Speech Sound Analysis
Oct 1, 2026Abner Hernandez, Tomás Arias Vergara, Andreas Maier +1Speech Processing Child Language Acquisition
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany · GITA Lab. Facultad de Ingenier´ıa. Universidad de Antioquia UdeA, Medell´ın, Colombia · Chair for AI in Healthcare and Medicine, Technical University of Munich, Munich, Germany
Cross-Linguistic Effects in Bilingual Phoneme BabyLMs
Sep 29, 2026Nikitas Theodoropoulos, Maria Lymperaiou, Giorgos FilandrianosMultilingual Language Models Child Language Acquisition
Independent Researcher · National Technical University of Athens · Instituto de Telecomunicações, Portugal
A retrospective analysis on the use of LLMs to study infant syntax learning
Sep 22, 2026Hélie Bazin, Anouk Barberousse, François YvonLLM Evaluation Language Modeling
SCAI, SND, ISIR · SND · MLIA
Modeling the Developmental Shift in Telicity Acquisition
Sep 16, 2026Ellie Xia, Parisa Kordjamshidi, Alan Hezao KeChild Language Acquisition Computational Psycholinguistics
Michigan State University · University of South Carolina
Which Forms of Caregiver Feedback Support Grammar Learning? A Reinforcement-Learning Study of Child-Like Language Models
Sep 8, 2026Jing Liu, Marianne Schweitzer, Abdellah FourtassiChild Language Acquisition
ENS, Université PSL, EHESS, CNRS, Paris, France · Aix Marseille Université, CNRS, LIS, Marseille, France
Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization
Sep 1, 2026Yixuan Wang, Freda Shi, Kanishka MisraSyntactic Generalization in Language Models Language Modeling
University of Waterloo Vector Institute · Department of Linguistics University of Texas at Austin
Lost but not erased: Finding traces of a forgotten language in neural speech models
Aug 26, 2026Peter Plantinga, Charlotte Moore, Peter W. Donhauser +2Second Language Acquisition Child Language Acquisition
From Exposure to Expectation: Frequency, Surprisal, and Language Across Development in Spanish
Aug 23, 2026Francisco Portillo LópezSurprisal Theory Child Language Acquisition
Universidad de Navarra, Pamplona, Spain
Children, but not language models, show accelerating returns in word learning
Aug 17, 2026Michael C. FrankChild Language Acquisition
Early Language Learning via Spreading Activation and Category Exploration in Complex Networks
Jul 7, 2026Salvatore CitraroChild Language Acquisition Computational Psycholinguistics
Institute of Information Science and Technologies “A. Faedo” (ISTI) National Research Council (CNR) Via G. Moruzzi, 1, 56124 Pisa, Italy · National Research Council (CNR) Via G. Moruzzi, 1, 56124 Pisa, Italy
Objects Before Words: Object-First Inductive Biases for Grounding Language in Child-View Video
Jun 11, 2026Sathira Silva, Abrham Kahsay Gebreselasie, Muhammad Umer Sheikh +3Object-Centric Representation Learning Egocentric Video Understanding
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · Weizmann Institute of Science, Rehovot, Israel
An ERP Study on Recursive Locative Processing in Mandarin-Speaking Children with Autism
Jun 4, 2026Xiaoyi Wang, Chenxi Fu, Ziman Zhuang +1Autism Spectrum Disorder Child Language Acquisition
Soochow University
Child-directed speech facilitates production, not comprehension, in BabyLMs
May 31, 2026Bastian Bunzeck, Sina ZarrießLanguage Model Pretraining LLM Evaluation
Computational Linguistics, Department of Linguistics Bielefeld University, Germany
ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood
May 28, 2026Tiantian Feng, Anfeng Xu, Xuan Shi +10Audio-Language Model Evaluation Speech Quality Assessment
University of Southern California · The Ohio State University · University of California, Los Angeles +3
Measuring Form and Function in Language Models
May 27, 2026Héctor Javier Vázquez Martínez, Charles YangLLM Evaluation Child Language Acquisition
University of Pennsylvania Department of Linguistics and Computer and Information Science
Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks
May 19, 2026Claire Hobbs, R. Thomas McCoyChild Language Acquisition Computational Psycholinguistics
Cognitive Science Program Yale University · Dept. of Linguistics & Wu Tsai Institute Yale University
CAIT: A Syntactic Parsing Toolkit for Child-Adult InTeractions
May 19, 2026Francesca Padovani, Xiulin Yang, Bastian Bunzeck +4Morphosyntactic Tagging Child Language Acquisition
Center for Language and Cognition (CLCG), University of Groningen · Georgetown University · Computational Linguistics, Department of Linguistics, Bielefeld University
Is Child-Directed Language Optimized for Word Learning? A Computational Study of Verb Meaning Acquisition
May 12, 2026Francesca Padovani, Jaap Jumelet, Yevgen Matusevych +1Child Language Acquisition Computational Psycholinguistics
Center for Language and Cognition (CLCG), University of Groningen
A Computational Operationalisation of Competing Maturational Theories of Syntactic Development via Statistical Grammar Induction
May 8, 2026Mila Marcheva, Suchir Salhan, Weiwei SunChild Language Acquisition Computational Psycholinguistics
Department of Computer Science & Technology, University of Cambridge
An ERP Study of Recursive Possessive Parsing in ASD Children and Its Cognitive Neuro Mechanisms
May 5, 2026Fu Chenxi, Wang Xiaoyi, Zhuang Ziman +1Autism Spectrum Disorder Child Language Acquisition
a School of Foreign Languages, Soochow University · b Ulink High School of Suzhou Industrial Park
Exemplar Retrieval Without Overhypothesis Induction: Limits of Distributional Sequence Learning in Early Word Learning
Apr 6, 2026Jon-Paul CacioliChild Language Acquisition Autoregressive Language Modeling
Independent Researcher
Baby Scale: Investigating Models Trained on Individual Children's Language Input
Mar 31, 2026Steven Y. Feng, Alvin W. M. Tan, Michael C. FrankLanguage Model Scaling Small Language Models
Stanford University
Infrequent Child-Directed Speech Is Bursty and May Draw Infant Vocalizations
Mar 25, 2026Margaret Cychosz, Adriana WeislederChild Language Acquisition
Dept. of Linguistics Stanford University Stanford, USA · Dept. of Communication Sciences and Disorders Northwestern University Evanston, USA
Repetition Without Exclusivity: Scale Sensitivity of Referential Mechanisms in Child-Scale Language Models
Mar 14, 2026Jon-Paul CacioliChild Language Acquisition
Independent Researcher Melbourne, Australia
Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priors
Mar 9, 2026Okko RäsänenChild Language Acquisition Computational Psycholinguistics
Signal Processing Research Centre, Tampere University, Finland
Modeling Grammatical Hypothesis Testing in Young Learners: A Sequence-Based Learning Analytics Study of Morphosyntactic Reasoning in an Interactive Game
Mar 2, 2026Thierry Geoffre, Trystan GeoffreChild Language Acquisition Computational Psycholinguistics
University of Luxembourg FHSE - Department of Education and Social Work Esch-sur-Alzette, Luxembourg · Université de Fribourg Institut de Plurilinguisme Fribourg, Switzerland
What Exactly do Children Receive in Language Acquisition? A Case Study on CHILDES with Automated Detection of Filler-Gap Dependencies
Mar 2, 2026Zhenghao Herbert Zhou, William Dai, Maya Viswanathan +3Constituency Parsing Child Language Acquisition
Department of Linguistics, Yale University · Department of Computer Science, Yale University · Wu Tsai Institute, Yale University

Oct 27, 2026J/K move · Enter open · S save

Specialization, Diversity, and Scaling in Child-Scale Language Models

Steven Y. Feng, Michael C. Frank

Stanford University

Small Language Models LLM Training Child Language Acquisition Syntactic Generalization in Language Models Next-Token Prediction

Open paper AskPDF arXiv

Modern language models are trained on far more language than children experience, but we know much less about learning from small, naturalistic datasets. We train small GPT-2 models on transcripts of speech with children from dense home recordings (BabyView) and on synthetic child-directed dialogue (TinyDialogues), varying the amount, source, and diversity of training data. Models trained on one child's language environment predict that environment substantially better than other children's environments. Much of this specialization is lexical and distributional: a simple 5-gram model reproduces the cross-child pattern (r=.91). Training on data from multiple children clearly improves prediction of pooled held-out language relative to training on a single child's input without a similarly clear improvement on grammatical benchmarks. Across data sizes, naturalistic and synthetic training inputs also produce different grammatical and lexical-semantic patterns, with important differences between grammatical phenomena. Together, these results show that small-data language learning depends not only on how much language a model sees, but on which environments it comes from and how well that input matches what the model is asked to predict.