<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-language">
    <titleInfo>
        <title>Do Language Models Understand Implicit Logical Meaning? A Case Study of Scope Ambiguity Resolution in Context</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jieun</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Suhyeon</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kunhui</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seung-Hoon</namePart>
        <namePart type="family">Na</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>Scope ambiguity arises when a single surface string admits multiple logical interpretations depending on how operators such as negation and indefinites interact. Prior work (Kamath et al. 2024) primarily evaluates scope sensitivity through output-level behavior, leaving open whether alternative interpretations are internally represented or merely reflected in shifted token probabilities.\par We introduce **an evidence-first, ambiguity-following diagnostic** that asks a more specific question: when the surface string is held constant and only contextual evidence biases interpretation, do transformer language models form distinct internal representations corresponding to alternative logical readings?\par To investigate this, we present **SCOPEx**, extending the dataset of Kamath et al. (2024) by systematically manipulating preceding context while keeping the ambiguous sentence identical. We further introduce passivized variants as syntactically less ambiguous controls. Using SCOPEx, we show that transformer LMs:\par (i) exhibit **systematic scope-sensitive behavior conditioned on context**, and\par (ii) form **separable hidden-state representations for alternative scope readings of the same surface string**.\par This divergence emerges in later layers and causally influences downstream predictions.</abstract>
    <identifier type="citekey">kim-etal-2026-language</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.806/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>18772</start>
            <end>18795</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Do Language Models Understand Implicit Logical Meaning? A Case Study of Scope Ambiguity Resolution in Context
%A Kim, Jieun
%A Park, Suhyeon
%A Lee, Kunhui
%A Na, Seung-Hoon
%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 kim-etal-2026-language
%X Scope ambiguity arises when a single surface string admits multiple logical interpretations depending on how operators such as negation and indefinites interact. Prior work (Kamath et al. 2024) primarily evaluates scope sensitivity through output-level behavior, leaving open whether alternative interpretations are internally represented or merely reflected in shifted token probabilities.\par We introduce **an evidence-first, ambiguity-following diagnostic** that asks a more specific question: when the surface string is held constant and only contextual evidence biases interpretation, do transformer language models form distinct internal representations corresponding to alternative logical readings?\par To investigate this, we present **SCOPEx**, extending the dataset of Kamath et al. (2024) by systematically manipulating preceding context while keeping the ambiguous sentence identical. We further introduce passivized variants as syntactically less ambiguous controls. Using SCOPEx, we show that transformer LMs:\par (i) exhibit **systematic scope-sensitive behavior conditioned on context**, and\par (ii) form **separable hidden-state representations for alternative scope readings of the same surface string**.\par This divergence emerges in later layers and causally influences downstream predictions.
%U https://aclanthology.org/2026.emnlp-main.806/
%P 18772-18795

Markdown (Informal)

[Do Language Models Understand Implicit Logical Meaning? A Case Study of Scope Ambiguity Resolution in Context](https://aclanthology.org/2026.emnlp-main.806/) (Kim et al., EMNLP 2026)

• Do Language Models Understand Implicit Logical Meaning? A Case Study of Scope Ambiguity Resolution in Context (Kim et al., EMNLP 2026)

ACL

• Jieun Kim, Suhyeon Park, Kunhui Lee, and Seung-Hoon Na. 2026. Do Language Models Understand Implicit Logical Meaning? A Case Study of Scope Ambiguity Resolution in Context. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 18772–18795, Budapest, Hungary. Association for Computational Linguistics.