<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="blackmore-stone-2025-llms">
    <titleInfo>
        <title>Can LLMs Disambiguate Grounded Language? The Case of PP Attachment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">John</namePart>
        <namePart type="family">Blackmore</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthew</namePart>
        <namePart type="family">Stone</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Kunilovskaya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie</namePart>
            <namePart type="family">Escribe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We explore the potential of large language models in resolving ambiguity in prepositional phrase attachments in grounded language. We find that when prompted in such a way that we can compute a probability of the respective attachment, models yield promising results. However, additional inputs from a measure of information structure may help improve prediction accuracy. We also investigate where we need more sophisticated tools, commonsense reasoning, world knowledge, and additional context to resolve ambiguity.</abstract>
    <identifier type="citekey">blackmore-stone-2025-llms</identifier>
    <location>
        <url>https://aclanthology.org/2025.ranlp-1.20/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>166</start>
            <end>174</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Can LLMs Disambiguate Grounded Language? The Case of PP Attachment
%A Blackmore, John
%A Stone, Matthew
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F blackmore-stone-2025-llms
%X We explore the potential of large language models in resolving ambiguity in prepositional phrase attachments in grounded language. We find that when prompted in such a way that we can compute a probability of the respective attachment, models yield promising results. However, additional inputs from a measure of information structure may help improve prediction accuracy. We also investigate where we need more sophisticated tools, commonsense reasoning, world knowledge, and additional context to resolve ambiguity.
%U https://aclanthology.org/2025.ranlp-1.20/
%P 166-174

Markdown (Informal)

[Can LLMs Disambiguate Grounded Language? The Case of PP Attachment](https://aclanthology.org/2025.ranlp-1.20/) (Blackmore & Stone, RANLP 2025)

• Can LLMs Disambiguate Grounded Language? The Case of PP Attachment (Blackmore & Stone, RANLP 2025)

ACL

• John Blackmore and Matthew Stone. 2025. Can LLMs Disambiguate Grounded Language? The Case of PP Attachment. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 166–174, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.