Query Timing Produces Opposite Positional Biases Between LLMs and Humans

Jasin Cekinmez; Addison J. Wu; Thomas L. Griffiths

Query Timing Produces Opposite Positional Biases Between LLMs and Humans

Jasin Cekinmez, Addison J. Wu, Thomas L. Griffiths

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 PDF.)

Authors concatenated from the text boxes above:

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

Abstract

Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood. Both primacy and recency biases have been observed in human judgments in response to evidence, but recent work suggest that when the listener updates their beliefs – during the presentation of evidence or only at the end – influences the presence of such effects. We investigate whether a similar phenomenon holds for LLMs, finding divergence from human behavior. These biases are more exacerbated in newer models compared to their predecessors.

Anthology ID:: 2026.findings-emnlp.1354
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 28741–28758
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.1354/
DOI:
Bibkey:
Cite (ACL):: Jasin Cekinmez, Addison J. Wu, and Thomas L. Griffiths. 2026. Query Timing Produces Opposite Positional Biases Between LLMs and Humans. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 28741–28758, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Query Timing Produces Opposite Positional Biases Between LLMs and Humans (Cekinmez et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.1354.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{cekinmez-etal-2026-query,
    title = "Query Timing Produces Opposite Positional Biases Between {LLM}s and Humans",
    author = "Cekinmez, Jasin  and
      Wu, Addison J.  and
      Griffiths, Thomas L.",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1354/",
    pages = "28741--28758",
    ISBN = "979-8-89176-462-0",
    abstract = "Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood. Both $\textit{primacy}$ and $\textit{recency}$ biases have been observed in human judgments in response to evidence, but recent work suggest that $\textit{when}$ the listener updates their beliefs {--} during the presentation of evidence or only at the end {--} influences the presence of such effects. We investigate whether a similar phenomenon holds for LLMs, finding divergence from human behavior. These biases are more exacerbated in newer models compared to their predecessors."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cekinmez-etal-2026-query">
    <titleInfo>
        <title>Query Timing Produces Opposite Positional Biases Between LLMs and Humans</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jasin</namePart>
        <namePart type="family">Cekinmez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Addison</namePart>
        <namePart type="given">J</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thomas</namePart>
        <namePart type="given">L</namePart>
        <namePart type="family">Griffiths</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood. Both primacy and recency biases have been observed in human judgments in response to evidence, but recent work suggest that when the listener updates their beliefs – during the presentation of evidence or only at the end – influences the presence of such effects. We investigate whether a similar phenomenon holds for LLMs, finding divergence from human behavior. These biases are more exacerbated in newer models compared to their predecessors.</abstract>
    <identifier type="citekey">cekinmez-etal-2026-query</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1354/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>28741</start>
            <end>28758</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Query Timing Produces Opposite Positional Biases Between LLMs and Humans
%A Cekinmez, Jasin
%A Wu, Addison J.
%A Griffiths, Thomas L.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F cekinmez-etal-2026-query
%X Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood. Both primacy and recency biases have been observed in human judgments in response to evidence, but recent work suggest that when the listener updates their beliefs – during the presentation of evidence or only at the end – influences the presence of such effects. We investigate whether a similar phenomenon holds for LLMs, finding divergence from human behavior. These biases are more exacerbated in newer models compared to their predecessors.
%U https://aclanthology.org/2026.findings-emnlp.1354/
%P 28741-28758

Download as File

Markdown (Informal)

[Query Timing Produces Opposite Positional Biases Between LLMs and Humans](https://aclanthology.org/2026.findings-emnlp.1354/) (Cekinmez et al., Findings 2026)

Query Timing Produces Opposite Positional Biases Between LLMs and Humans (Cekinmez et al., Findings 2026)

ACL

Jasin Cekinmez, Addison J. Wu, and Thomas L. Griffiths. 2026. Query Timing Produces Opposite Positional Biases Between LLMs and Humans. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 28741–28758, Budapest, Hungary. Association for Computational Linguistics.