<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2026-one">
    <titleInfo>
        <title>Which one is banana man? Evaluating vision–language models in multi-turn pragmatic interpretation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Alvin</namePart>
        <namePart type="given">Wei</namePart>
        <namePart type="given">Ming</namePart>
        <namePart type="family">Tan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ben</namePart>
        <namePart type="family">Prystawski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Veronica</namePart>
        <namePart type="family">Boyce</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>Flexible adaptation to context and shared pragmatic intuitions contribute to smooth human conversation. Iterated reference games—in which players repeatedly pick out novel referents using language—present a test case for agents’ ability to perform context-sensitive pragmatic reasoning in multi-turn linguistic environments. We tested humans and vision–language models on their ability to identify the intended meaning of descriptions produced in iterated reference games, varying the provided context in terms of amount, order, and relevance. While humans performed well consistently, the models we evaluated could make use of prior context to interpret humans’ referring expressions, but they struggled to build up the relevant context to interpret those expressions effectively. Our results suggest that the models we evaluated lack core skills needed for efficient linguistic collaboration.</abstract>
    <identifier type="citekey">tan-etal-2026-one</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.548/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>12595</start>
            <end>12611</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Which one is banana man? Evaluating vision–language models in multi-turn pragmatic interpretation
%A Tan, Alvin Wei Ming
%A Prystawski, Ben
%A Boyce, Veronica
%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 tan-etal-2026-one
%X Flexible adaptation to context and shared pragmatic intuitions contribute to smooth human conversation. Iterated reference games—in which players repeatedly pick out novel referents using language—present a test case for agents’ ability to perform context-sensitive pragmatic reasoning in multi-turn linguistic environments. We tested humans and vision–language models on their ability to identify the intended meaning of descriptions produced in iterated reference games, varying the provided context in terms of amount, order, and relevance. While humans performed well consistently, the models we evaluated could make use of prior context to interpret humans’ referring expressions, but they struggled to build up the relevant context to interpret those expressions effectively. Our results suggest that the models we evaluated lack core skills needed for efficient linguistic collaboration.
%U https://aclanthology.org/2026.emnlp-main.548/
%P 12595-12611

Markdown (Informal)

[Which one is banana man? Evaluating vision–language models in multi-turn pragmatic interpretation](https://aclanthology.org/2026.emnlp-main.548/) (Tan et al., EMNLP 2026)

• Which one is banana man? Evaluating vision–language models in multi-turn pragmatic interpretation (Tan et al., EMNLP 2026)

ACL

• Alvin Wei Ming Tan, Ben Prystawski, and Veronica Boyce. 2026. Which one is banana man? Evaluating vision–language models in multi-turn pragmatic interpretation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 12595–12611, Budapest, Hungary. Association for Computational Linguistics.