@inproceedings{wang-2026-multilingual,
title = "Do Multilingual Models Represent Colour Differently Across Languages? The Gap Is in the Vocabularies",
author = "Wang, Rong",
editor = "Ranaldi, Leonardo and
Pucci, Giulia and
Ranaldi, Federico and
Valentino, Marco and
Birch, Alexandra and
Zanzotto, Fabio Massimo",
booktitle = "The Proceedings of the Workshop on Open Reasoning Across Cultures Languages ({ORACLE})",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.oracle-main.33/",
pages = "476--483",
ISBN = "979-8-89176-483-5",
abstract = "Languages differ in how much of a word{'}s meaning is visible in its spelling. A colour term may name its own category in its written form or give no hint of it at all, and languages differ widely in how many of their terms do. This matters for a standard test. A model is said to represent colour well if it places two colour words close together whenever the colours they name look alike, and far apart when they do not. Comparing two languages means running that test on each language{'}s own colour words. But where the spelling already names the category, a model can place the words correctly by reading their spelling alone, so the test is easier in some languages than in others. We quantify this for four languages and two multilingual models, Qwen2.5-7B and Llama-3.1-8B. The proportion of terms whose written form names their category ranges from 0{\%} to 92{\%} across our four lexicons, and the proportion of the score that disappears once written-form similarity is removed tracks it closely (r = 0.84): 0{--}5{\%} in Spanish and English, 32{--}71{\%} in Chinese, 37{--}42{\%} in German. On the raw test Chinese scores higher than English. Counting only what the model could not have got from spelling, English is ahead. We then test all four languages on the same 43 colours, so that no vocabulary gives more away than any other. Their scores become close enough that we cannot separate them at this sample size, though a finer comparison shows the four languages still arrange those colours somewhat differently. Much of what a conventional comparison reports then looks like a fact about how each language spells its colour words rather than about the model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-2026-multilingual">
<titleInfo>
<title>Do Multilingual Models Represent Colour Differently Across Languages? The Gap Is in the Vocabularies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rong</namePart>
<namePart type="family">Wang</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>The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Pucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valentino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="given">Massimo</namePart>
<namePart type="family">Zanzotto</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">979-8-89176-483-5</identifier>
</relatedItem>
<abstract>Languages differ in how much of a word’s meaning is visible in its spelling. A colour term may name its own category in its written form or give no hint of it at all, and languages differ widely in how many of their terms do. This matters for a standard test. A model is said to represent colour well if it places two colour words close together whenever the colours they name look alike, and far apart when they do not. Comparing two languages means running that test on each language’s own colour words. But where the spelling already names the category, a model can place the words correctly by reading their spelling alone, so the test is easier in some languages than in others. We quantify this for four languages and two multilingual models, Qwen2.5-7B and Llama-3.1-8B. The proportion of terms whose written form names their category ranges from 0% to 92% across our four lexicons, and the proportion of the score that disappears once written-form similarity is removed tracks it closely (r = 0.84): 0–5% in Spanish and English, 32–71% in Chinese, 37–42% in German. On the raw test Chinese scores higher than English. Counting only what the model could not have got from spelling, English is ahead. We then test all four languages on the same 43 colours, so that no vocabulary gives more away than any other. Their scores become close enough that we cannot separate them at this sample size, though a finer comparison shows the four languages still arrange those colours somewhat differently. Much of what a conventional comparison reports then looks like a fact about how each language spells its colour words rather than about the model.</abstract>
<identifier type="citekey">wang-2026-multilingual</identifier>
<location>
<url>https://aclanthology.org/2026.oracle-main.33/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>476</start>
<end>483</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Multilingual Models Represent Colour Differently Across Languages? The Gap Is in the Vocabularies
%A Wang, Rong
%Y Ranaldi, Leonardo
%Y Pucci, Giulia
%Y Ranaldi, Federico
%Y Valentino, Marco
%Y Birch, Alexandra
%Y Zanzotto, Fabio Massimo
%S The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-483-5
%F wang-2026-multilingual
%X Languages differ in how much of a word’s meaning is visible in its spelling. A colour term may name its own category in its written form or give no hint of it at all, and languages differ widely in how many of their terms do. This matters for a standard test. A model is said to represent colour well if it places two colour words close together whenever the colours they name look alike, and far apart when they do not. Comparing two languages means running that test on each language’s own colour words. But where the spelling already names the category, a model can place the words correctly by reading their spelling alone, so the test is easier in some languages than in others. We quantify this for four languages and two multilingual models, Qwen2.5-7B and Llama-3.1-8B. The proportion of terms whose written form names their category ranges from 0% to 92% across our four lexicons, and the proportion of the score that disappears once written-form similarity is removed tracks it closely (r = 0.84): 0–5% in Spanish and English, 32–71% in Chinese, 37–42% in German. On the raw test Chinese scores higher than English. Counting only what the model could not have got from spelling, English is ahead. We then test all four languages on the same 43 colours, so that no vocabulary gives more away than any other. Their scores become close enough that we cannot separate them at this sample size, though a finer comparison shows the four languages still arrange those colours somewhat differently. Much of what a conventional comparison reports then looks like a fact about how each language spells its colour words rather than about the model.
%U https://aclanthology.org/2026.oracle-main.33/
%P 476-483
Markdown (Informal)
[Do Multilingual Models Represent Colour Differently Across Languages? The Gap Is in the Vocabularies](https://aclanthology.org/2026.oracle-main.33/) (Wang, ORACLE 2026)
ACL