@inproceedings{cacioli-2026-repetition,
title = "Repetition Without Exclusivity: Scale Sensitivity of Referential Mechanisms in Child-Scale Language Models",
author = "Cacioli, Jon-Paul",
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.19/",
pages = "240--249",
ISBN = "979-8-89176-475-0",
abstract = "We present the first systematic evaluation of mutual exclusivity (ME), the bias to map novel words to novel referents, in text-only language models trained on child-directed speech. We operationalise ME as referential suppression and train 45 GPT-2 models (2.9M{--}33.5M parameters; 5{--}20 epochs on AO-CHILDES; 5 seeds) on a pre-registered ME battery. Across all 9 cells of the grid, models show robust anti-ME repetition priming, the opposite of ME, in 85{--}100{\%} of items (all p {\ensuremath{<}} 2.5 {\texttimes} 10{\ensuremath{^-}}{\textonesuperior}{\textthreesuperior}), attenuating with improved language modelling (Spearman {\ensuremath{\rho}} = {\ensuremath{-}}0.533) but never crossing zero. A positive control on pretrained GPT-2 (124M{--}1.5B) shows the same priming, attenuating with scale but never reversing into significant ME, confirming the battery can detect suppression when present. The dissociation also holds on a size-matched non-CDS corpus (WikiText). A context-dependence diagnostic further shows that apparent ME-like patterns with nonce tokens reflect embedding similarity, not referential disambiguation. We connect this to the grounded cognition literature, where ME does emerge in visually grounded models, and argue that referential grounding, or another mechanism instantiating competition among candidate referents, may be required for ME-like behaviour to emerge."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cacioli-2026-repetition">
<titleInfo>
<title>Repetition Without Exclusivity: Scale Sensitivity of Referential Mechanisms in Child-Scale Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jon-Paul</namePart>
<namePart type="family">Cacioli</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>We present the first systematic evaluation of mutual exclusivity (ME), the bias to map novel words to novel referents, in text-only language models trained on child-directed speech. We operationalise ME as referential suppression and train 45 GPT-2 models (2.9M–33.5M parameters; 5–20 epochs on AO-CHILDES; 5 seeds) on a pre-registered ME battery. Across all 9 cells of the grid, models show robust anti-ME repetition priming, the opposite of ME, in 85–100% of items (all p \ensuremath< 2.5 × 10\ensuremath⁻¹³), attenuating with improved language modelling (Spearman \ensuremathρ = \ensuremath-0.533) but never crossing zero. A positive control on pretrained GPT-2 (124M–1.5B) shows the same priming, attenuating with scale but never reversing into significant ME, confirming the battery can detect suppression when present. The dissociation also holds on a size-matched non-CDS corpus (WikiText). A context-dependence diagnostic further shows that apparent ME-like patterns with nonce tokens reflect embedding similarity, not referential disambiguation. We connect this to the grounded cognition literature, where ME does emerge in visually grounded models, and argue that referential grounding, or another mechanism instantiating competition among candidate referents, may be required for ME-like behaviour to emerge.</abstract>
<identifier type="citekey">cacioli-2026-repetition</identifier>
<location>
<url>https://aclanthology.org/2026.babylm-main.19/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>240</start>
<end>249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Repetition Without Exclusivity: Scale Sensitivity of Referential Mechanisms in Child-Scale Language Models
%A Cacioli, Jon-Paul
%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 cacioli-2026-repetition
%X We present the first systematic evaluation of mutual exclusivity (ME), the bias to map novel words to novel referents, in text-only language models trained on child-directed speech. We operationalise ME as referential suppression and train 45 GPT-2 models (2.9M–33.5M parameters; 5–20 epochs on AO-CHILDES; 5 seeds) on a pre-registered ME battery. Across all 9 cells of the grid, models show robust anti-ME repetition priming, the opposite of ME, in 85–100% of items (all p \ensuremath< 2.5 × 10\ensuremath⁻¹³), attenuating with improved language modelling (Spearman \ensuremathρ = \ensuremath-0.533) but never crossing zero. A positive control on pretrained GPT-2 (124M–1.5B) shows the same priming, attenuating with scale but never reversing into significant ME, confirming the battery can detect suppression when present. The dissociation also holds on a size-matched non-CDS corpus (WikiText). A context-dependence diagnostic further shows that apparent ME-like patterns with nonce tokens reflect embedding similarity, not referential disambiguation. We connect this to the grounded cognition literature, where ME does emerge in visually grounded models, and argue that referential grounding, or another mechanism instantiating competition among candidate referents, may be required for ME-like behaviour to emerge.
%U https://aclanthology.org/2026.babylm-main.19/
%P 240-249
Markdown (Informal)
[Repetition Without Exclusivity: Scale Sensitivity of Referential Mechanisms in Child-Scale Language Models](https://aclanthology.org/2026.babylm-main.19/) (Cacioli, BabyLM 2026)
ACL