Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication

Peter Zeng; Amie J. Paige; Weiling Li; Susan E. Brennan; Owen Rambow; Cameron Robert Jones

doi:10.18653/2026.emnlp-main.704

Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication

Peter Zeng, Amie J. Paige, Weiling Li, Susan Brennan, Owen Rambow, Cameron Robert Jones

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

Two recent studies (Jones et al. (2026); Zeng et al. (2026)) reach apparently contradictory conclusions about whether LVLMs can coordinate on efficient referring expressions. We control for task differences between the studies while directly comparing their prompting styles. We replicate the finding that models can coordinate efficient referring expressions when explicitly prompted to do so, suggesting that other task differences are not responsible for divergent results. However, we also find that the same models fail to infer the need for communicative efficiency from a more implicit prompt, highlighting critical differences between how humans and AI systems communicate.

Anthology ID:: 2026.emnlp-main.704
Volume:: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: EMNLP
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 16269–16285
Language:
URL:: https://aclanthology.org/2026.emnlp-main.704/
DOI:: 10.18653/2026.emnlp-main.704
Bibkey:
Cite (ACL):: Peter Zeng, Amie J. Paige, Weiling Li, Susan Brennan, Owen Rambow, and Cameron Robert Jones. 2026. Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 16269–16285, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication (Zeng et al., EMNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.emnlp-main.704.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{zeng-etal-2026-implicit,
    title = "Implicit vs. Explicit Prompting Strategies for {LVLM}s in Referential Communication",
    author = "Zeng, Peter  and
      Paige, Amie J.  and
      Li, Weiling  and
      Brennan, Susan  and
      Rambow, Owen  and
      Jones, Cameron Robert",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.704/",
    doi = "10.18653/2026.emnlp-main.704",
    pages = "16269--16285",
    ISBN = "979-8-89176-459-0",
    abstract = "Two recent studies (Jones et al. (2026); Zeng et al. (2026)) reach apparently contradictory conclusions about whether LVLMs can coordinate on efficient referring expressions. We control for task differences between the studies while directly comparing their prompting styles. We replicate the finding that models can coordinate efficient referring expressions when \textit{explicitly} prompted to do so, suggesting that other task differences are not responsible for divergent results. However, we also find that the same models fail to infer the need for communicative efficiency from a more \textit{implicit} prompt, highlighting critical differences between how humans and AI systems communicate."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2026-implicit">
    <titleInfo>
        <title>Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Peter</namePart>
        <namePart type="family">Zeng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amie</namePart>
        <namePart type="given">J</namePart>
        <namePart type="family">Paige</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weiling</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Susan</namePart>
        <namePart type="family">Brennan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Owen</namePart>
        <namePart type="family">Rambow</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cameron</namePart>
        <namePart type="given">Robert</namePart>
        <namePart type="family">Jones</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Two recent studies (Jones et al. (2026); Zeng et al. (2026)) reach apparently contradictory conclusions about whether LVLMs can coordinate on efficient referring expressions. We control for task differences between the studies while directly comparing their prompting styles. We replicate the finding that models can coordinate efficient referring expressions when explicitly prompted to do so, suggesting that other task differences are not responsible for divergent results. However, we also find that the same models fail to infer the need for communicative efficiency from a more implicit prompt, highlighting critical differences between how humans and AI systems communicate.</abstract>
    <identifier type="citekey">zeng-etal-2026-implicit</identifier>
    <identifier type="doi">10.18653/2026.emnlp-main.704</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.704/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>16269</start>
            <end>16285</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication
%A Zeng, Peter
%A Paige, Amie J.
%A Li, Weiling
%A Brennan, Susan
%A Rambow, Owen
%A Jones, Cameron Robert
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zeng-etal-2026-implicit
%X Two recent studies (Jones et al. (2026); Zeng et al. (2026)) reach apparently contradictory conclusions about whether LVLMs can coordinate on efficient referring expressions. We control for task differences between the studies while directly comparing their prompting styles. We replicate the finding that models can coordinate efficient referring expressions when explicitly prompted to do so, suggesting that other task differences are not responsible for divergent results. However, we also find that the same models fail to infer the need for communicative efficiency from a more implicit prompt, highlighting critical differences between how humans and AI systems communicate.
%R 10.18653/2026.emnlp-main.704
%U https://aclanthology.org/2026.emnlp-main.704/
%U https://doi.org/10.18653/2026.emnlp-main.704
%P 16269-16285

Download as File

Markdown (Informal)

[Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication](https://aclanthology.org/2026.emnlp-main.704/) (Zeng et al., EMNLP 2026)

Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication (Zeng et al., EMNLP 2026)

ACL

Peter Zeng, Amie J. Paige, Weiling Li, Susan Brennan, Owen Rambow, and Cameron Robert Jones. 2026. Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 16269–16285, Budapest, Hungary. Association for Computational Linguistics.