@inproceedings{chesi-etal-2026-exploring,
title = "Exploring Linguistic Parameters in {LM}s",
author = "Chesi, Cristiano and
Fusco, Achille and
Formichi, Guido and
Rossi, Sarah and
Cygan, Hanna B. and
Sgrizzi, Tommaso and
Zanollo, Asya",
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.53/",
pages = "659--677",
ISBN = "979-8-89176-475-0",
abstract = "This work is an attempt to frame Principles and Parameters theory (Yang et al 2017) within the BabyLM Multilingual perspective. First, we compared tokenization and architectural strategies that make the incremental nature of language acquisition and processing more or less transparent (recurrent versus attention-based architectures). We then assessed our trained models with respect to specific linguistic generalizations, including morphological decomposition, learning trajectories, and binary parametric linguistic options. We observed that (i) morphologically informed tokenizers yield consistent benefits, both in terms of learning trajectories and performance on downstream minimal-pair tasks; (ii) recurrent architectures are substantially more data-efficient, converging earlier and achieving slightly better results on downstream evaluation tasks; and (iii) the parameter set-up objective leads to modest improvements and not in all the expected linguistic domains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chesi-etal-2026-exploring">
<titleInfo>
<title>Exploring Linguistic Parameters in LMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cristiano</namePart>
<namePart type="family">Chesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Achille</namePart>
<namePart type="family">Fusco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guido</namePart>
<namePart type="family">Formichi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Rossi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Cygan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Sgrizzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asya</namePart>
<namePart type="family">Zanollo</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>This work is an attempt to frame Principles and Parameters theory (Yang et al 2017) within the BabyLM Multilingual perspective. First, we compared tokenization and architectural strategies that make the incremental nature of language acquisition and processing more or less transparent (recurrent versus attention-based architectures). We then assessed our trained models with respect to specific linguistic generalizations, including morphological decomposition, learning trajectories, and binary parametric linguistic options. We observed that (i) morphologically informed tokenizers yield consistent benefits, both in terms of learning trajectories and performance on downstream minimal-pair tasks; (ii) recurrent architectures are substantially more data-efficient, converging earlier and achieving slightly better results on downstream evaluation tasks; and (iii) the parameter set-up objective leads to modest improvements and not in all the expected linguistic domains.</abstract>
<identifier type="citekey">chesi-etal-2026-exploring</identifier>
<location>
<url>https://aclanthology.org/2026.babylm-main.53/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>659</start>
<end>677</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Linguistic Parameters in LMs
%A Chesi, Cristiano
%A Fusco, Achille
%A Formichi, Guido
%A Rossi, Sarah
%A Cygan, Hanna B.
%A Sgrizzi, Tommaso
%A Zanollo, Asya
%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 chesi-etal-2026-exploring
%X This work is an attempt to frame Principles and Parameters theory (Yang et al 2017) within the BabyLM Multilingual perspective. First, we compared tokenization and architectural strategies that make the incremental nature of language acquisition and processing more or less transparent (recurrent versus attention-based architectures). We then assessed our trained models with respect to specific linguistic generalizations, including morphological decomposition, learning trajectories, and binary parametric linguistic options. We observed that (i) morphologically informed tokenizers yield consistent benefits, both in terms of learning trajectories and performance on downstream minimal-pair tasks; (ii) recurrent architectures are substantially more data-efficient, converging earlier and achieving slightly better results on downstream evaluation tasks; and (iii) the parameter set-up objective leads to modest improvements and not in all the expected linguistic domains.
%U https://aclanthology.org/2026.babylm-main.53/
%P 659-677
Markdown (Informal)
[Exploring Linguistic Parameters in LMs](https://aclanthology.org/2026.babylm-main.53/) (Chesi et al., BabyLM 2026)
ACL
- Cristiano Chesi, Achille Fusco, Guido Formichi, Sarah Rossi, Hanna B. Cygan, Tommaso Sgrizzi, and Asya Zanollo. 2026. Exploring Linguistic Parameters in LMs. In Proceedings of the Second BabyLM Workshop, pages 659–677, Budapest, Hungary. Association for Computational Linguistics.