@inproceedings{csuros-etal-2026-cross,
title = "Cross-linguistic Readability and Controllable Difficulty: A Corpus-Based Comparison of Human and {LLM} Translations of Children{'}s Literature in {R}omanian",
author = "Csuros, Karla and
Chitez, Madalina and
Rogobete, Roxana",
editor = "Di Nunzio, Giorgio Maria and
Vezzani, Federica and
Ermakova, Liana and
Azarbonyad, Hosein and
Kamps, Jaap",
booktitle = "Proceedings of the 2nd Workshop on Evaluating Text Difficulty in a Multilingual Context ({D}e{T}erm{I}t! 2026)",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.determit-1.1/",
doi = "10.63317/4yotwqa9fti4",
pages = "1--11",
abstract = "Translation can systematically alter text difficulty, particularly when moving into morphologically rich languages. This study examines whether readability-constrained Large Language Models (LLMs) can mitigate difficulty shifts observed in English{--}Romanian translation of children{'}s literature. We construct a paired four-condition corpus comprising English originals, published Romanian translations, readability-constrained LLM translations, and human readability adaptations (12 aligned passages; approx. 23,000 words). Readability is assessed using a Romanian grade-level index (LEMI) designed to be educationally comparable to Flesch{--}Kincaid Grade Level (FKGL), the cross-linguistic LIX metric, and morphologically informed measures derived from spaCy. Published Romanian translations are significantly more difficult than their English originals, showing higher LIX scores, grade-level estimates, and increased morphological variation. Readability-constrained LLM translation substantially reduces difficulty relative to the published versions (median delta approx. {\ensuremath{-}}1.46 grade levels), with significant decreases in LIX, morphological feature density, and lexical diversity (MTLD). Human adaptation yields a smaller reduction (median delta approx. {\ensuremath{-}}0.26). Although the direct comparison between LLM and human adaptation is marginal (p = .055, r = 0.64), LLM outputs generally produce larger reductions. These findings demonstrate that translation-induced difficulty shifts are measurable and that controllable LLM translation can modulate readability across structural, lexical, and morphological dimensions in multilingual educational contexts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="csuros-etal-2026-cross">
<titleInfo>
<title>Cross-linguistic Readability and Controllable Difficulty: A Corpus-Based Comparison of Human and LLM Translations of Children’s Literature in Romanian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karla</namePart>
<namePart type="family">Csuros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madalina</namePart>
<namePart type="family">Chitez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roxana</namePart>
<namePart type="family">Rogobete</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Evaluating Text Difficulty in a Multilingual Context (DeTermIt! 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giorgio</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Di Nunzio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federica</namePart>
<namePart type="family">Vezzani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liana</namePart>
<namePart type="family">Ermakova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Azarbonyad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Kamps</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translation can systematically alter text difficulty, particularly when moving into morphologically rich languages. This study examines whether readability-constrained Large Language Models (LLMs) can mitigate difficulty shifts observed in English–Romanian translation of children’s literature. We construct a paired four-condition corpus comprising English originals, published Romanian translations, readability-constrained LLM translations, and human readability adaptations (12 aligned passages; approx. 23,000 words). Readability is assessed using a Romanian grade-level index (LEMI) designed to be educationally comparable to Flesch–Kincaid Grade Level (FKGL), the cross-linguistic LIX metric, and morphologically informed measures derived from spaCy. Published Romanian translations are significantly more difficult than their English originals, showing higher LIX scores, grade-level estimates, and increased morphological variation. Readability-constrained LLM translation substantially reduces difficulty relative to the published versions (median delta approx. \ensuremath-1.46 grade levels), with significant decreases in LIX, morphological feature density, and lexical diversity (MTLD). Human adaptation yields a smaller reduction (median delta approx. \ensuremath-0.26). Although the direct comparison between LLM and human adaptation is marginal (p = .055, r = 0.64), LLM outputs generally produce larger reductions. These findings demonstrate that translation-induced difficulty shifts are measurable and that controllable LLM translation can modulate readability across structural, lexical, and morphological dimensions in multilingual educational contexts.</abstract>
<identifier type="citekey">csuros-etal-2026-cross</identifier>
<identifier type="doi">10.63317/4yotwqa9fti4</identifier>
<location>
<url>https://aclanthology.org/2026.determit-1.1/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-linguistic Readability and Controllable Difficulty: A Corpus-Based Comparison of Human and LLM Translations of Children’s Literature in Romanian
%A Csuros, Karla
%A Chitez, Madalina
%A Rogobete, Roxana
%Y Di Nunzio, Giorgio Maria
%Y Vezzani, Federica
%Y Ermakova, Liana
%Y Azarbonyad, Hosein
%Y Kamps, Jaap
%S Proceedings of the 2nd Workshop on Evaluating Text Difficulty in a Multilingual Context (DeTermIt! 2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F csuros-etal-2026-cross
%X Translation can systematically alter text difficulty, particularly when moving into morphologically rich languages. This study examines whether readability-constrained Large Language Models (LLMs) can mitigate difficulty shifts observed in English–Romanian translation of children’s literature. We construct a paired four-condition corpus comprising English originals, published Romanian translations, readability-constrained LLM translations, and human readability adaptations (12 aligned passages; approx. 23,000 words). Readability is assessed using a Romanian grade-level index (LEMI) designed to be educationally comparable to Flesch–Kincaid Grade Level (FKGL), the cross-linguistic LIX metric, and morphologically informed measures derived from spaCy. Published Romanian translations are significantly more difficult than their English originals, showing higher LIX scores, grade-level estimates, and increased morphological variation. Readability-constrained LLM translation substantially reduces difficulty relative to the published versions (median delta approx. \ensuremath-1.46 grade levels), with significant decreases in LIX, morphological feature density, and lexical diversity (MTLD). Human adaptation yields a smaller reduction (median delta approx. \ensuremath-0.26). Although the direct comparison between LLM and human adaptation is marginal (p = .055, r = 0.64), LLM outputs generally produce larger reductions. These findings demonstrate that translation-induced difficulty shifts are measurable and that controllable LLM translation can modulate readability across structural, lexical, and morphological dimensions in multilingual educational contexts.
%R 10.63317/4yotwqa9fti4
%U https://aclanthology.org/2026.determit-1.1/
%U https://doi.org/10.63317/4yotwqa9fti4
%P 1-11
Markdown (Informal)
[Cross-linguistic Readability and Controllable Difficulty: A Corpus-Based Comparison of Human and LLM Translations of Children’s Literature in Romanian](https://aclanthology.org/2026.determit-1.1/) (Csuros et al., DeTermIt 2026)
ACL