@inproceedings{varis-doggett-kennedy-2026-miss,
title = "Miss Universal Grammar: Pretraining {B}aby{LM}s with Linguistic and Non-Linguistic Sources",
author = "Varis Doggett, Erika and
Kennedy, Mary",
editor = "Choshen, Leshem and
Cotterell, Ryan and
Gul, Mustafa Omer and
Jumelet, Jaap and
Linzen, Tal and
Mueller, Aaron and
Salhan, Suchir and
Shah, Raj Sanjay and
Warstadt, Alex and
Wilcox, Ethan Gotlieb",
booktitle = "Proceedings of the Second {B}aby{LM} Workshop",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.babylm-main.56/",
pages = "702--721",
ISBN = "979-8-89176-475-0",
abstract = "Inspired by linguistic theory and recent work exploring linguistic biasing of neural networks, we propose a ``Universal Grammar'' (UG) pretraining paradigm for transformer-based neural networks, preparing the network to learn language more effectively, especially in low data volume scenarios. We accomplish this ``universal'' pretraining with a combination of synthetic language-like sequences created with a context-free grammar, biological sequence sources like protein amino acids, and material sources like crystal structures. Experiments with the BabyLM Challenge datasets show improved language acquisition in English, Dutch, and Chinese with our MissUniverse models, compared to not using ``UG'' pretraining. This pretraining paradigm has interesting implications for both the future of language models, and potentially how we think about human Universal Grammar."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varis-doggett-kennedy-2026-miss">
<titleInfo>
<title>Miss Universal Grammar: Pretraining BabyLMs with Linguistic and Non-Linguistic Sources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erika</namePart>
<namePart type="family">Varis Doggett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Kennedy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second BabyLM Workshop</title>
</titleInfo>
<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">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">Suchir</namePart>
<namePart type="family">Salhan</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-475-0</identifier>
</relatedItem>
<abstract>Inspired by linguistic theory and recent work exploring linguistic biasing of neural networks, we propose a “Universal Grammar” (UG) pretraining paradigm for transformer-based neural networks, preparing the network to learn language more effectively, especially in low data volume scenarios. We accomplish this “universal” pretraining with a combination of synthetic language-like sequences created with a context-free grammar, biological sequence sources like protein amino acids, and material sources like crystal structures. Experiments with the BabyLM Challenge datasets show improved language acquisition in English, Dutch, and Chinese with our MissUniverse models, compared to not using “UG” pretraining. This pretraining paradigm has interesting implications for both the future of language models, and potentially how we think about human Universal Grammar.</abstract>
<identifier type="citekey">varis-doggett-kennedy-2026-miss</identifier>
<location>
<url>https://aclanthology.org/2026.babylm-main.56/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>702</start>
<end>721</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Miss Universal Grammar: Pretraining BabyLMs with Linguistic and Non-Linguistic Sources
%A Varis Doggett, Erika
%A Kennedy, Mary
%Y Choshen, Leshem
%Y Cotterell, Ryan
%Y Gul, Mustafa Omer
%Y Jumelet, Jaap
%Y Linzen, Tal
%Y Mueller, Aaron
%Y Salhan, Suchir
%Y Shah, Raj Sanjay
%Y Warstadt, Alex
%Y Wilcox, Ethan Gotlieb
%S Proceedings of the Second BabyLM Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-475-0
%F varis-doggett-kennedy-2026-miss
%X Inspired by linguistic theory and recent work exploring linguistic biasing of neural networks, we propose a “Universal Grammar” (UG) pretraining paradigm for transformer-based neural networks, preparing the network to learn language more effectively, especially in low data volume scenarios. We accomplish this “universal” pretraining with a combination of synthetic language-like sequences created with a context-free grammar, biological sequence sources like protein amino acids, and material sources like crystal structures. Experiments with the BabyLM Challenge datasets show improved language acquisition in English, Dutch, and Chinese with our MissUniverse models, compared to not using “UG” pretraining. This pretraining paradigm has interesting implications for both the future of language models, and potentially how we think about human Universal Grammar.
%U https://aclanthology.org/2026.babylm-main.56/
%P 702-721
Markdown (Informal)
[Miss Universal Grammar: Pretraining BabyLMs with Linguistic and Non-Linguistic Sources](https://aclanthology.org/2026.babylm-main.56/) (Varis Doggett & Kennedy, BabyLM 2026)
ACL