@inproceedings{fiandra-etal-2025-large,
title = "Large Language Models and Children Have Different Learning Trajectories in Determiner Acquisition",
author = "Fiandra, Olivia La and
Fernandez Echeverri, Nathalie and
Shafto, Patrick and
Feldman, Naomi H.",
editor = "Charpentier, Lucas and
Choshen, Leshem and
Cotterell, Ryan and
Gul, Mustafa Omer and
Hu, Michael Y. and
Liu, Jing and
Jumelet, Jaap and
Linzen, Tal and
Mueller, Aaron and
Ross, Candace and
Shah, Raj Sanjay and
Warstadt, Alex and
Wilcox, Ethan Gotlieb and
Williams, Adina",
booktitle = "Proceedings of the First BabyLM Workshop",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.babylm-main.8/",
pages = "100--108",
ISBN = "TODO",
abstract = "Large language models are often compared to human learners based on the amount of training data required or the end state capabilities of a learner, yet less attention has been given to differences in their language learning process. This study uses determiner acquisition as a case study to characterize how LLMs and children differ in their learning processes. By analyzing annotated speech samples from specified age ranges of four children and intermediate training checkpoints of the Pythia-70m language model, we trace the learners' learning paths of definite and indefinite determiner use. Our results reveal a divergence: the children first produce the indefinite determiner, while the model first produces the definite determiner. This difference reflects underlying differences in the learning goals and mechanisms of models and children. Framing language learning as movement over distributions of linguistic features makes the learning process visible and offers an alternative approach for comparing humans and language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fiandra-etal-2025-large">
<titleInfo>
<title>Large Language Models and Children Have Different Learning Trajectories in Determiner Acquisition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivia</namePart>
<namePart type="given">La</namePart>
<namePart type="family">Fiandra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathalie</namePart>
<namePart type="family">Fernandez Echeverri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Shafto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First BabyLM Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Charpentier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="given">Omer</namePart>
<namePart type="family">Gul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">Y</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Jumelet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Candace</namePart>
<namePart type="family">Ross</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="given">Sanjay</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Warstadt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="given">Gotlieb</namePart>
<namePart type="family">Wilcox</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adina</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">TODO</identifier>
</relatedItem>
<abstract>Large language models are often compared to human learners based on the amount of training data required or the end state capabilities of a learner, yet less attention has been given to differences in their language learning process. This study uses determiner acquisition as a case study to characterize how LLMs and children differ in their learning processes. By analyzing annotated speech samples from specified age ranges of four children and intermediate training checkpoints of the Pythia-70m language model, we trace the learners’ learning paths of definite and indefinite determiner use. Our results reveal a divergence: the children first produce the indefinite determiner, while the model first produces the definite determiner. This difference reflects underlying differences in the learning goals and mechanisms of models and children. Framing language learning as movement over distributions of linguistic features makes the learning process visible and offers an alternative approach for comparing humans and language models.</abstract>
<identifier type="citekey">fiandra-etal-2025-large</identifier>
<location>
<url>https://aclanthology.org/2025.babylm-main.8/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>100</start>
<end>108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Language Models and Children Have Different Learning Trajectories in Determiner Acquisition
%A Fiandra, Olivia La
%A Fernandez Echeverri, Nathalie
%A Shafto, Patrick
%A Feldman, Naomi H.
%Y Charpentier, Lucas
%Y Choshen, Leshem
%Y Cotterell, Ryan
%Y Gul, Mustafa Omer
%Y Hu, Michael Y.
%Y Liu, Jing
%Y Jumelet, Jaap
%Y Linzen, Tal
%Y Mueller, Aaron
%Y Ross, Candace
%Y Shah, Raj Sanjay
%Y Warstadt, Alex
%Y Wilcox, Ethan Gotlieb
%Y Williams, Adina
%S Proceedings of the First BabyLM Workshop
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ TODO
%F fiandra-etal-2025-large
%X Large language models are often compared to human learners based on the amount of training data required or the end state capabilities of a learner, yet less attention has been given to differences in their language learning process. This study uses determiner acquisition as a case study to characterize how LLMs and children differ in their learning processes. By analyzing annotated speech samples from specified age ranges of four children and intermediate training checkpoints of the Pythia-70m language model, we trace the learners’ learning paths of definite and indefinite determiner use. Our results reveal a divergence: the children first produce the indefinite determiner, while the model first produces the definite determiner. This difference reflects underlying differences in the learning goals and mechanisms of models and children. Framing language learning as movement over distributions of linguistic features makes the learning process visible and offers an alternative approach for comparing humans and language models.
%U https://aclanthology.org/2025.babylm-main.8/
%P 100-108
Markdown (Informal)
[Large Language Models and Children Have Different Learning Trajectories in Determiner Acquisition](https://aclanthology.org/2025.babylm-main.8/) (Fiandra et al., BabyLM 2025)
ACL