@inproceedings{xu-etal-2026-babyconceptlm,
title = "{B}aby{C}oncept{LM}: Exploring Dynamic Concept Computation under Restricted Language Exposure",
author = "Xu, Yizhe and
Song, Ming and
He, Danni and
Liu, Jianghao and
Wang, Yitong and
Cai, Qing",
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.61/",
pages = "779--804",
ISBN = "979-8-89176-475-0",
abstract = "Human language learning takes place under limited exposure and is shaped by structured regularities in the input, whereas standard Transformers apply a largely uniform sequence of computations at every token position. We ask whether dynamic latent segmentation can provide a useful inductive bias for language modeling under BabyLM-scale data constraints. BabyConceptLM causally encodes tokens, groups contextual states into learned contiguous latent segments, processes the shorter sequence with a deeper latent-level backbone, and returns to token resolution through a leakage-safe causal readout. We evaluate two profiles using recipe-matched token-only controls, with analyses of computational cost and segmentation behavior. Across English, multilingual, and Chinese comparisons, BabyConceptLM trails matched token-only controls by 0.60{--}1.47 points. Estimated padding-aware dense-forward FLOPs are reduced by 26{\%} and 39{\%} for the English and multilingual 5/8/3 models, respectively, but increase for the Chinese 2/4/2 configuration. Segmentation audits show weak alignment with word boundaries and predominantly length-driven behavior, with the larger model frequently reaching its eight-token segment cap. These results show that latent segmentation can yield a favorable compute{--}accuracy trade-off in some configurations, but does not by itself produce linguistically structured units or improved predictive performance. BabyConceptLM serves as a diagnostic test of hierarchical latent computation under restricted language exposure."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-babyconceptlm">
<titleInfo>
<title>BabyConceptLM: Exploring Dynamic Concept Computation under Restricted Language Exposure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yizhe</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danni</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianghao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yitong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Cai</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>Human language learning takes place under limited exposure and is shaped by structured regularities in the input, whereas standard Transformers apply a largely uniform sequence of computations at every token position. We ask whether dynamic latent segmentation can provide a useful inductive bias for language modeling under BabyLM-scale data constraints. BabyConceptLM causally encodes tokens, groups contextual states into learned contiguous latent segments, processes the shorter sequence with a deeper latent-level backbone, and returns to token resolution through a leakage-safe causal readout. We evaluate two profiles using recipe-matched token-only controls, with analyses of computational cost and segmentation behavior. Across English, multilingual, and Chinese comparisons, BabyConceptLM trails matched token-only controls by 0.60–1.47 points. Estimated padding-aware dense-forward FLOPs are reduced by 26% and 39% for the English and multilingual 5/8/3 models, respectively, but increase for the Chinese 2/4/2 configuration. Segmentation audits show weak alignment with word boundaries and predominantly length-driven behavior, with the larger model frequently reaching its eight-token segment cap. These results show that latent segmentation can yield a favorable compute–accuracy trade-off in some configurations, but does not by itself produce linguistically structured units or improved predictive performance. BabyConceptLM serves as a diagnostic test of hierarchical latent computation under restricted language exposure.</abstract>
<identifier type="citekey">xu-etal-2026-babyconceptlm</identifier>
<location>
<url>https://aclanthology.org/2026.babylm-main.61/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>779</start>
<end>804</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BabyConceptLM: Exploring Dynamic Concept Computation under Restricted Language Exposure
%A Xu, Yizhe
%A Song, Ming
%A He, Danni
%A Liu, Jianghao
%A Wang, Yitong
%A Cai, Qing
%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 xu-etal-2026-babyconceptlm
%X Human language learning takes place under limited exposure and is shaped by structured regularities in the input, whereas standard Transformers apply a largely uniform sequence of computations at every token position. We ask whether dynamic latent segmentation can provide a useful inductive bias for language modeling under BabyLM-scale data constraints. BabyConceptLM causally encodes tokens, groups contextual states into learned contiguous latent segments, processes the shorter sequence with a deeper latent-level backbone, and returns to token resolution through a leakage-safe causal readout. We evaluate two profiles using recipe-matched token-only controls, with analyses of computational cost and segmentation behavior. Across English, multilingual, and Chinese comparisons, BabyConceptLM trails matched token-only controls by 0.60–1.47 points. Estimated padding-aware dense-forward FLOPs are reduced by 26% and 39% for the English and multilingual 5/8/3 models, respectively, but increase for the Chinese 2/4/2 configuration. Segmentation audits show weak alignment with word boundaries and predominantly length-driven behavior, with the larger model frequently reaching its eight-token segment cap. These results show that latent segmentation can yield a favorable compute–accuracy trade-off in some configurations, but does not by itself produce linguistically structured units or improved predictive performance. BabyConceptLM serves as a diagnostic test of hierarchical latent computation under restricted language exposure.
%U https://aclanthology.org/2026.babylm-main.61/
%P 779-804
Markdown (Informal)
[BabyConceptLM: Exploring Dynamic Concept Computation under Restricted Language Exposure](https://aclanthology.org/2026.babylm-main.61/) (Xu et al., BabyLM 2026)
ACL