<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goworek-dubossarsky-2026-lexical">
    <titleInfo>
        <title>Lexical Redefinition Reveals Context-Sensitive Instruction Following</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Roksana</namePart>
        <namePart type="family">Goworek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haim</namePart>
        <namePart type="family">Dubossarsky</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 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Rui</namePart>
            <namePart type="family">Sousa-Silva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henrique</namePart>
            <namePart type="family">Lopes Cardoso</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maarit</namePart>
            <namePart type="family">Koponen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Pareja-Lora</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">979-8-89176-471-2</identifier>
    </relatedItem>
    <abstract>How do language models reconcile conflicting contextual evidence within a prompt? We study this question using lexical redefinition, where an explicit instruction specifies how a word should be interpreted and a subsequent sentence provides additional evidence through its usage. Across 870 word pairs, we find that lexical redefinitions are not applied as fixed rules. Instead, the behaviour depends systematically on the relationship between the explicit instruction and the intervening sentence: the contextualised usage can preserve, weaken, or completely reverse the instruction. These results suggest that the interpretation of an explicit instruction remains sensitive to subsequent contextual evidence. Lexical redefinition therefore provides a controlled behavioural paradigm for studying how language models integrate multiple sources of information within a prompt.</abstract>
    <identifier type="citekey">goworek-dubossarsky-2026-lexical</identifier>
    <location>
        <url>https://aclanthology.org/2026.luhme-1.17/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>215</start>
            <end>226</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Lexical Redefinition Reveals Context-Sensitive Instruction Following
%A Goworek, Roksana
%A Dubossarsky, Haim
%Y Sousa-Silva, Rui
%Y Lopes Cardoso, Henrique
%Y Koponen, Maarit
%Y Pareja-Lora, Antonio
%S Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-471-2
%F goworek-dubossarsky-2026-lexical
%X How do language models reconcile conflicting contextual evidence within a prompt? We study this question using lexical redefinition, where an explicit instruction specifies how a word should be interpreted and a subsequent sentence provides additional evidence through its usage. Across 870 word pairs, we find that lexical redefinitions are not applied as fixed rules. Instead, the behaviour depends systematically on the relationship between the explicit instruction and the intervening sentence: the contextualised usage can preserve, weaken, or completely reverse the instruction. These results suggest that the interpretation of an explicit instruction remains sensitive to subsequent contextual evidence. Lexical redefinition therefore provides a controlled behavioural paradigm for studying how language models integrate multiple sources of information within a prompt.
%U https://aclanthology.org/2026.luhme-1.17/
%P 215-226

Markdown (Informal)

[Lexical Redefinition Reveals Context-Sensitive Instruction Following](https://aclanthology.org/2026.luhme-1.17/) (Goworek & Dubossarsky, LUHME 2026)

• Lexical Redefinition Reveals Context-Sensitive Instruction Following (Goworek & Dubossarsky, LUHME 2026)

ACL

• Roksana Goworek and Haim Dubossarsky. 2026. Lexical Redefinition Reveals Context-Sensitive Instruction Following. In Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026), pages 215–226, Budapest, Hungary. Association for Computational Linguistics.