<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="desai-nair-2026-filling">
    <titleInfo>
        <title>Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Atrey</namePart>
        <namePart type="family">Desai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sathvik</namePart>
        <namePart type="family">Nair</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>For humans, filler-gap dependencies require a shared representation across different syntactic constructions. Although causal analyses suggest this may also be true for LLMs (Boguraev et al., 2025), it is still unclear if such a representation also exists for language models trained on developmentally feasible quantities of data. We applied Distributed Alignment Search (DAS, Geiger et al. (2024)) to checkpoints of a language model from the BabyLM challenge (Warstadt et al., 2023), to evaluate whether representations of filler-gap dependencies transfer between wh-questions and topicalization, which greatly vary in terms of their input frequency. Our results suggest shared, yet item-sensitive mechanisms may develop with limited training data. More importantly, LMs still require far more data than humans to learn comparable generalizations, highlighting the need for language-specific biases in models of language acquisition.</abstract>
    <identifier type="citekey">desai-nair-2026-filling</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.1737/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>34799</start>
            <end>34815</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints?
%A Desai, Atrey
%A Nair, Sathvik
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F desai-nair-2026-filling
%X For humans, filler-gap dependencies require a shared representation across different syntactic constructions. Although causal analyses suggest this may also be true for LLMs (Boguraev et al., 2025), it is still unclear if such a representation also exists for language models trained on developmentally feasible quantities of data. We applied Distributed Alignment Search (DAS, Geiger et al. (2024)) to checkpoints of a language model from the BabyLM challenge (Warstadt et al., 2023), to evaluate whether representations of filler-gap dependencies transfer between wh-questions and topicalization, which greatly vary in terms of their input frequency. Our results suggest shared, yet item-sensitive mechanisms may develop with limited training data. More importantly, LMs still require far more data than humans to learn comparable generalizations, highlighting the need for language-specific biases in models of language acquisition.
%U https://aclanthology.org/2026.findings-acl.1737/
%P 34799-34815

Markdown (Informal)

[Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints?](https://aclanthology.org/2026.findings-acl.1737/) (Desai & Nair, Findings 2026)

• Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints? (Desai & Nair, Findings 2026)

ACL

• Atrey Desai and Sathvik Nair. 2026. Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints?. In Findings of the Association for Computational Linguistics: ACL 2026, pages 34799–34815, San Diego, California, United States. Association for Computational Linguistics.