@inproceedings{xu-liu-2026-beyond,
title = "Beyond Over-Simplification and Over-Personalization: Lexical Complexity Prediction for Leveled Reading",
author = "Xu, Huidan and
Liu, Ying",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.941/",
pages = "21689--21705",
ISBN = "979-8-89176-459-0",
abstract = "Lexical Complexity Prediction (LCP) in real-world scenarios, particularly in language education, is often limited by the trade-off between overly simplified general models and unscalable personalized ones. To address this, we introduce LCP for Leveled Reading (LCP-LR), a task aiming to operationalize group-level personalization by identifying complex words relative to specific proficiency levels, thereby balancing pedagogical guidance and scalability. We construct the first large-scale benchmark dataset for this task, comprising 100,917 instance annotations across 1,401 leveled texts. Furthermore, we propose Dual-Prior Adversarial Learning (DPAL), a framework that incorporates word- and text-level difficulty priors alongside adversarial debiasing to mitigate the model{'}s over-reliance on simplistic absolute difficulty shortcuts. Experimental results show that DPAL significantly outperforms both conventional pre-trained baselines and large language models, improving the Macro of the best baseline (XLNet) from 74.19{\%} to 77.81{\%}. Our evaluations also reveal that large language models underperform in zero- and few-shot settings without fine-tuning or Chain-of-Thought prompting. Overall, this work promotes the practical deployment of LCP and lays a crucial technical foundation for dynamic text adaptation within leveled reading."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-liu-2026-beyond">
<titleInfo>
<title>Beyond Over-Simplification and Over-Personalization: Lexical Complexity Prediction for Leveled Reading</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huidan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Liu</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Lexical Complexity Prediction (LCP) in real-world scenarios, particularly in language education, is often limited by the trade-off between overly simplified general models and unscalable personalized ones. To address this, we introduce LCP for Leveled Reading (LCP-LR), a task aiming to operationalize group-level personalization by identifying complex words relative to specific proficiency levels, thereby balancing pedagogical guidance and scalability. We construct the first large-scale benchmark dataset for this task, comprising 100,917 instance annotations across 1,401 leveled texts. Furthermore, we propose Dual-Prior Adversarial Learning (DPAL), a framework that incorporates word- and text-level difficulty priors alongside adversarial debiasing to mitigate the model’s over-reliance on simplistic absolute difficulty shortcuts. Experimental results show that DPAL significantly outperforms both conventional pre-trained baselines and large language models, improving the Macro of the best baseline (XLNet) from 74.19% to 77.81%. Our evaluations also reveal that large language models underperform in zero- and few-shot settings without fine-tuning or Chain-of-Thought prompting. Overall, this work promotes the practical deployment of LCP and lays a crucial technical foundation for dynamic text adaptation within leveled reading.</abstract>
<identifier type="citekey">xu-liu-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.941/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>21689</start>
<end>21705</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Over-Simplification and Over-Personalization: Lexical Complexity Prediction for Leveled Reading
%A Xu, Huidan
%A Liu, Ying
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F xu-liu-2026-beyond
%X Lexical Complexity Prediction (LCP) in real-world scenarios, particularly in language education, is often limited by the trade-off between overly simplified general models and unscalable personalized ones. To address this, we introduce LCP for Leveled Reading (LCP-LR), a task aiming to operationalize group-level personalization by identifying complex words relative to specific proficiency levels, thereby balancing pedagogical guidance and scalability. We construct the first large-scale benchmark dataset for this task, comprising 100,917 instance annotations across 1,401 leveled texts. Furthermore, we propose Dual-Prior Adversarial Learning (DPAL), a framework that incorporates word- and text-level difficulty priors alongside adversarial debiasing to mitigate the model’s over-reliance on simplistic absolute difficulty shortcuts. Experimental results show that DPAL significantly outperforms both conventional pre-trained baselines and large language models, improving the Macro of the best baseline (XLNet) from 74.19% to 77.81%. Our evaluations also reveal that large language models underperform in zero- and few-shot settings without fine-tuning or Chain-of-Thought prompting. Overall, this work promotes the practical deployment of LCP and lays a crucial technical foundation for dynamic text adaptation within leveled reading.
%U https://aclanthology.org/2026.emnlp-main.941/
%P 21689-21705
Markdown (Informal)
[Beyond Over-Simplification and Over-Personalization: Lexical Complexity Prediction for Leveled Reading](https://aclanthology.org/2026.emnlp-main.941/) (Xu & Liu, EMNLP 2026)
ACL