@inproceedings{dini-etal-2025-human,
title = "From Human Reading to {NLM} Understanding: Evaluating the Role of Eye-Tracking Data in Encoder-Based Models",
author = "Dini, Luca and
Domenichelli, Lucia and
Brunato, Dominique and
Dell{'}Orletta, Felice",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.870/",
doi = "10.18653/v1/2025.acl-long.870",
pages = "17796--17813",
ISBN = "979-8-89176-251-0",
abstract = "Cognitive signals, particularly eye-tracking data, offer valuable insights into human language processing. Leveraging eye-gaze data from the Ghent Eye-Tracking Corpus, we conducted a series of experiments to examine how integrating knowledge of human reading behavior impacts Neural Language Models (NLMs) across multiple dimensions: task performance, attention mechanisms, and the geometry of their embedding space. We explored several fine-tuning methodologies to inject eye-tracking features into the models. Our results reveal that incorporating these features does not degrade downstream task performance, enhances alignment between model attention and human attention patterns, and compresses the geometry of the embedding space."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dini-etal-2025-human">
<titleInfo>
<title>From Human Reading to NLM Understanding: Evaluating the Role of Eye-Tracking Data in Encoder-Based Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Dini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Domenichelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominique</namePart>
<namePart type="family">Brunato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Cognitive signals, particularly eye-tracking data, offer valuable insights into human language processing. Leveraging eye-gaze data from the Ghent Eye-Tracking Corpus, we conducted a series of experiments to examine how integrating knowledge of human reading behavior impacts Neural Language Models (NLMs) across multiple dimensions: task performance, attention mechanisms, and the geometry of their embedding space. We explored several fine-tuning methodologies to inject eye-tracking features into the models. Our results reveal that incorporating these features does not degrade downstream task performance, enhances alignment between model attention and human attention patterns, and compresses the geometry of the embedding space.</abstract>
<identifier type="citekey">dini-etal-2025-human</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.870</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.870/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>17796</start>
<end>17813</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Human Reading to NLM Understanding: Evaluating the Role of Eye-Tracking Data in Encoder-Based Models
%A Dini, Luca
%A Domenichelli, Lucia
%A Brunato, Dominique
%A Dell’Orletta, Felice
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F dini-etal-2025-human
%X Cognitive signals, particularly eye-tracking data, offer valuable insights into human language processing. Leveraging eye-gaze data from the Ghent Eye-Tracking Corpus, we conducted a series of experiments to examine how integrating knowledge of human reading behavior impacts Neural Language Models (NLMs) across multiple dimensions: task performance, attention mechanisms, and the geometry of their embedding space. We explored several fine-tuning methodologies to inject eye-tracking features into the models. Our results reveal that incorporating these features does not degrade downstream task performance, enhances alignment between model attention and human attention patterns, and compresses the geometry of the embedding space.
%R 10.18653/v1/2025.acl-long.870
%U https://aclanthology.org/2025.acl-long.870/
%U https://doi.org/10.18653/v1/2025.acl-long.870
%P 17796-17813
Markdown (Informal)
[From Human Reading to NLM Understanding: Evaluating the Role of Eye-Tracking Data in Encoder-Based Models](https://aclanthology.org/2025.acl-long.870/) (Dini et al., ACL 2025)
ACL