@inproceedings{sauberli-etal-2026-exploring,
title = "Exploring Cognitively Informed Sentence Simplification with Gaze-Guided Text Generation",
author = {S{\"a}uberli, Andreas and
Frassinelli, Diego and
Plank, Barbara},
editor = {Acart{\"u}rk, Cengiz and
Can, Burcu and
Nasir, Jamal and
{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
booktitle = "Proceedings fo the Second International Workshop on Eye-Tracking Resources and Evaluation for Human-Aligned {NLP}",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELDA",
url = "https://aclanthology.org/2026.gaze4nlp-1.3/",
doi = "10.63317/3cju9gvduaga",
pages = "16--23",
abstract = "Automatic text simplification has mostly relied on human judgments when it comes to what is considered easy or difficult to read. Eye movements while reading can offer a more direct and objective signal of processing effort and reading ease. In this paper, we explore gaze-guided text generation (GGTG), an approach to control reading ease in generated texts, and assess its use for sentence simplification. GGTG employs a gaze model that is trained to predict eye-tracking measures such as reading times or regression rates, which are then used to rerank next-token probabilities generated by a language model. We evaluated the approach on an English sentence simplification benchmark and found gains in automatic evaluation metrics, although the simplification operations are mostly limited to the lexical level. Its modular nature also allows GGTG to be combined with other simplification techniques such as prompting or fine-tuning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sauberli-etal-2026-exploring">
<titleInfo>
<title>Exploring Cognitively Informed Sentence Simplification with Gaze-Guided Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Säuberli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Frassinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</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 fo the Second International Workshop on Eye-Tracking Resources and Evaluation for Human-Aligned NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cengiz</namePart>
<namePart type="family">Acartürk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamal</namePart>
<namePart type="family">Nasir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELDA</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic text simplification has mostly relied on human judgments when it comes to what is considered easy or difficult to read. Eye movements while reading can offer a more direct and objective signal of processing effort and reading ease. In this paper, we explore gaze-guided text generation (GGTG), an approach to control reading ease in generated texts, and assess its use for sentence simplification. GGTG employs a gaze model that is trained to predict eye-tracking measures such as reading times or regression rates, which are then used to rerank next-token probabilities generated by a language model. We evaluated the approach on an English sentence simplification benchmark and found gains in automatic evaluation metrics, although the simplification operations are mostly limited to the lexical level. Its modular nature also allows GGTG to be combined with other simplification techniques such as prompting or fine-tuning.</abstract>
<identifier type="citekey">sauberli-etal-2026-exploring</identifier>
<identifier type="doi">10.63317/3cju9gvduaga</identifier>
<location>
<url>https://aclanthology.org/2026.gaze4nlp-1.3/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>16</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Cognitively Informed Sentence Simplification with Gaze-Guided Text Generation
%A Säuberli, Andreas
%A Frassinelli, Diego
%A Plank, Barbara
%Y Acartürk, Cengiz
%Y Can, Burcu
%Y Nasir, Jamal
%Y Çöltekin, Çağrı
%S Proceedings fo the Second International Workshop on Eye-Tracking Resources and Evaluation for Human-Aligned NLP
%D 2026
%8 May
%I ELDA
%C Palma de Mallorca, Spain
%F sauberli-etal-2026-exploring
%X Automatic text simplification has mostly relied on human judgments when it comes to what is considered easy or difficult to read. Eye movements while reading can offer a more direct and objective signal of processing effort and reading ease. In this paper, we explore gaze-guided text generation (GGTG), an approach to control reading ease in generated texts, and assess its use for sentence simplification. GGTG employs a gaze model that is trained to predict eye-tracking measures such as reading times or regression rates, which are then used to rerank next-token probabilities generated by a language model. We evaluated the approach on an English sentence simplification benchmark and found gains in automatic evaluation metrics, although the simplification operations are mostly limited to the lexical level. Its modular nature also allows GGTG to be combined with other simplification techniques such as prompting or fine-tuning.
%R 10.63317/3cju9gvduaga
%U https://aclanthology.org/2026.gaze4nlp-1.3/
%U https://doi.org/10.63317/3cju9gvduaga
%P 16-23
Markdown (Informal)
[Exploring Cognitively Informed Sentence Simplification with Gaze-Guided Text Generation](https://aclanthology.org/2026.gaze4nlp-1.3/) (Säuberli et al., Gaze4NLP 2026)
ACL