<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fried-2026-symbolic">
    <titleInfo>
        <title>When Symbolic Analyses Mislead: Resolution Sensitivity in Neural Language Representations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Matthew</namePart>
        <namePart type="family">Fried</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Recent representation analyses have reported structure-like or invariant behavior even in randomly initialized transformers, motivating the interpretation that aspects of linguistic structure may be architectural rather than learned. We show that such conclusions can be artifacts of coarse symbolic discretization. We formalize symbolic analysis of neural representations as operating over discretized activation trajectories and identify symbolic resolution as a critical, previously uncontrolled variable. Varying resolution reveals a sharp collapse of apparent similarity in random models, while pretrained models maintain stable, operator-selective differentiation across all tested resolutions. We introduce resolution stability as a necessary validity criterion for symbolic and automata-based analyses, providing a falsifiable, architecture-agnostic diagnostic for auditing internal linguistic structure in neural language models.</abstract>
    <identifier type="citekey">fried-2026-symbolic</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.9/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>163</start>
            <end>172</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When Symbolic Analyses Mislead: Resolution Sensitivity in Neural Language Representations
%A Fried, Matthew
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F fried-2026-symbolic
%X Recent representation analyses have reported structure-like or invariant behavior even in randomly initialized transformers, motivating the interpretation that aspects of linguistic structure may be architectural rather than learned. We show that such conclusions can be artifacts of coarse symbolic discretization. We formalize symbolic analysis of neural representations as operating over discretized activation trajectories and identify symbolic resolution as a critical, previously uncontrolled variable. Varying resolution reveals a sharp collapse of apparent similarity in random models, while pretrained models maintain stable, operator-selective differentiation across all tested resolutions. We introduce resolution stability as a necessary validity criterion for symbolic and automata-based analyses, providing a falsifiable, architecture-agnostic diagnostic for auditing internal linguistic structure in neural language models.
%U https://aclanthology.org/2026.findings-emnlp.9/
%P 163-172

Markdown (Informal)

[When Symbolic Analyses Mislead: Resolution Sensitivity in Neural Language Representations](https://aclanthology.org/2026.findings-emnlp.9/) (Fried, Findings 2026)

• When Symbolic Analyses Mislead: Resolution Sensitivity in Neural Language Representations (Fried, Findings 2026)

ACL

• Matthew Fried. 2026. When Symbolic Analyses Mislead: Resolution Sensitivity in Neural Language Representations. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 163–172, Budapest, Hungary. Association for Computational Linguistics.