Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal

Lukas Mielczarek; Laura Kallmeyer

doi:10.63317/4xn5igbwvtd5

Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the external publication .)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Anthology ID:: 2026.cmcl-1.15
Volume:: Proceedings of the 15th Workshop on Cognitive Modeling and Computational Linguistics
Month:: May
Year:: 2026
Address:: Palma, Mallorca (Spain)
Editors:: Byung-Doh Oh, Tatsuki Kuribayashi, Giulia Rambelli, Ece Takmaz, Philipp Wicke, Jixing Li, Ryo Yoshida
Venues:: CMCL | WS
SIG:
Publisher:: ELRA Language Resources Association (ELRA)
Note:
Pages:: 188–202
Language:
External URL:: https://lrec.elra.info/lrec2026-ws-cmcl-15
DOI:: 10.63317/4xn5igbwvtd5
Bibkey:
Cite (ACL):: Lukas Mielczarek and Laura Kallmeyer. 2026. Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal. In Proceedings of the 15th Workshop on Cognitive Modeling and Computational Linguistics, pages 188–202, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):: Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal (Mielczarek & Kallmeyer, CMCL 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{mielczarek-kallmeyer-2026-aggregated,
    title = "Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal",
    author = "Mielczarek, Lukas  and
      Kallmeyer, Laura",
    editor = "Oh, Byung-Doh  and
      Kuribayashi, Tatsuki  and
      Rambelli, Giulia  and
      Takmaz, Ece  and
      Wicke, Philipp  and
      Li, Jixing  and
      Yoshida, Ryo",
    booktitle = "Proceedings of the 15th Workshop on Cognitive Modeling and Computational Linguistics",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmcl-1.15/",
    doi = "10.63317/4xn5igbwvtd5",
    pages = "188--202"
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mielczarek-kallmeyer-2026-aggregated">
    <titleInfo>
        <title>Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lukas</namePart>
        <namePart type="family">Mielczarek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Laura</namePart>
        <namePart type="family">Kallmeyer</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 15th Workshop on Cognitive Modeling and Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Byung-Doh</namePart>
            <namePart type="family">Oh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tatsuki</namePart>
            <namePart type="family">Kuribayashi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Giulia</namePart>
            <namePart type="family">Rambelli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ece</namePart>
            <namePart type="family">Takmaz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Philipp</namePart>
            <namePart type="family">Wicke</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jixing</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ryo</namePart>
            <namePart type="family">Yoshida</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>
    <identifier type="citekey">mielczarek-kallmeyer-2026-aggregated</identifier>
    <identifier type="doi">10.63317/4xn5igbwvtd5</identifier>
    <location>
        <url>https://aclanthology.org/2026.cmcl-1.15/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>188</start>
            <end>202</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal
%A Mielczarek, Lukas
%A Kallmeyer, Laura
%Y Oh, Byung-Doh
%Y Kuribayashi, Tatsuki
%Y Rambelli, Giulia
%Y Takmaz, Ece
%Y Wicke, Philipp
%Y Li, Jixing
%Y Yoshida, Ryo
%S Proceedings of the 15th Workshop on Cognitive Modeling and Computational Linguistics
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F mielczarek-kallmeyer-2026-aggregated
%R 10.63317/4xn5igbwvtd5
%U https://aclanthology.org/2026.cmcl-1.15/
%U https://doi.org/10.63317/4xn5igbwvtd5
%P 188-202

Download as File

Markdown (Informal)

[Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal](https://aclanthology.org/2026.cmcl-1.15/) (Mielczarek & Kallmeyer, CMCL 2026)

Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal (Mielczarek & Kallmeyer, CMCL 2026)

ACL

Lukas Mielczarek and Laura Kallmeyer. 2026. Aggregated Transformer Attention Measures Predict Reading Times Beyond Surprisal. In Proceedings of the 15th Workshop on Cognitive Modeling and Computational Linguistics, pages 188–202, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).