@inproceedings{carranza-navarrete-etal-2026-assessing,
title = "Assessing Small Language Models as Text Simplification Evaluators",
author = "Carranza Navarrete, David and
Bakker, Jan and
Kamps, Jaap",
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-1.9/",
doi = "10.63317/54qbtfwgkz9j",
pages = "83--86",
abstract = "Text simplification requires reliable automatic evaluation, yet existing learnable metrics such as LENS and LENS-SALSA are specialized and costly to develop. Moreover, it remains unclear how these metrics compare to using large language models (LLMs) as evaluators. Exploring this question is important because LLM-based evaluation could make simplification research and deployment more flexible and easier to adapt than training new task-specific metrics for each setting. In this work, we empirically compare several small, open-weight instruction-tuned LLMs with LENS and LENS-SALSA in both reference-based and reference-free evaluation settings. We measure their alignment with human judgments across multiple datasets. Our results provide insight into when small LLMs can serve as effective evaluators and when specialized metrics remain preferable, informing the design of future evaluation pipelines for text simplification and related text generation tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carranza-navarrete-etal-2026-assessing">
<titleInfo>
<title>Assessing Small Language Models as Text Simplification Evaluators</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Carranza Navarrete</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Bakker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Kamps</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>Text simplification requires reliable automatic evaluation, yet existing learnable metrics such as LENS and LENS-SALSA are specialized and costly to develop. Moreover, it remains unclear how these metrics compare to using large language models (LLMs) as evaluators. Exploring this question is important because LLM-based evaluation could make simplification research and deployment more flexible and easier to adapt than training new task-specific metrics for each setting. In this work, we empirically compare several small, open-weight instruction-tuned LLMs with LENS and LENS-SALSA in both reference-based and reference-free evaluation settings. We measure their alignment with human judgments across multiple datasets. Our results provide insight into when small LLMs can serve as effective evaluators and when specialized metrics remain preferable, informing the design of future evaluation pipelines for text simplification and related text generation tasks.</abstract>
<identifier type="citekey">carranza-navarrete-etal-2026-assessing</identifier>
<identifier type="doi">10.63317/54qbtfwgkz9j</identifier>
<location>
<url>https://aclanthology.org/2026.determit-1.9/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>83</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing Small Language Models as Text Simplification Evaluators
%A Carranza Navarrete, David
%A Bakker, Jan
%A Kamps, Jaap
%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 carranza-navarrete-etal-2026-assessing
%X Text simplification requires reliable automatic evaluation, yet existing learnable metrics such as LENS and LENS-SALSA are specialized and costly to develop. Moreover, it remains unclear how these metrics compare to using large language models (LLMs) as evaluators. Exploring this question is important because LLM-based evaluation could make simplification research and deployment more flexible and easier to adapt than training new task-specific metrics for each setting. In this work, we empirically compare several small, open-weight instruction-tuned LLMs with LENS and LENS-SALSA in both reference-based and reference-free evaluation settings. We measure their alignment with human judgments across multiple datasets. Our results provide insight into when small LLMs can serve as effective evaluators and when specialized metrics remain preferable, informing the design of future evaluation pipelines for text simplification and related text generation tasks.
%R 10.63317/54qbtfwgkz9j
%U https://aclanthology.org/2026.determit-1.9/
%U https://doi.org/10.63317/54qbtfwgkz9j
%P 83-86
Markdown (Informal)
[Assessing Small Language Models as Text Simplification Evaluators](https://aclanthology.org/2026.determit-1.9/) (Carranza Navarrete et al., DeTermIt 2026)
ACL