<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grewal-2026-decodability">
    <titleInfo>
        <title>Decodability Is Not Computation: Examining Probing Claims</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kabir</namePart>
        <namePart type="given">Singh</namePart>
        <namePart type="family">Grewal</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 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dana</namePart>
            <namePart type="family">Arad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yonatan</namePart>
            <namePart type="family">Belinkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hanjie</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nils</namePart>
            <namePart type="family">Feldhus</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aaron</namePart>
            <namePart type="family">Mueller</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hosein</namePart>
            <namePart type="family">Mohebbi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gabriele</namePart>
            <namePart type="family">Sarti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Martin</namePart>
            <namePart type="family">Tutek</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">979-8-89176-476-7</identifier>
    </relatedItem>
    <abstract>High probe accuracy does not by itself establish that a language model computes and uses the decoded value. We examine this inference in a syntax-sensitive arithmetic testbed: Llama-3.1-8B often fails multiplication when an operand is wrapped in parentheses or an additive identity. In the primary operand band, an input-only linear baseline nearly matches the original hidden-state probe’s regression R² \approx 0.96. A classical variance decomposition gives an analytical headroom of only 0.031 for this baseline class. In wider bands, selection-separated reanalysis instead finds positive activation advantages, which increase with regularization tuning; joint input-and-activation probes also improve over the baseline. These predictive gains are distinct from exact integer recovery and causal use. In the primary band, tested answer-site steering and state transplants produce small average output shifts and no observed donor-answer emissions, whereas operand-site interventions produce large effects. Operand access is necessary, with a strong bottleneck at one attention layer. The causal tests do not cover the wider-band predictive gains. We advocate explicit input baselines, matched causal tests, and positive controls, with conclusions restricted to the distributions, representations, and interventions actually examined.</abstract>
    <identifier type="citekey">grewal-2026-decodability</identifier>
    <location>
        <url>https://aclanthology.org/2026.blackboxnlp-1.14/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>201</start>
            <end>219</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Decodability Is Not Computation: Examining Probing Claims
%A Grewal, Kabir Singh
%Y Arad, Dana
%Y Belinkov, Yonatan
%Y Chen, Hanjie
%Y Feldhus, Nils
%Y Mueller, Aaron
%Y Mohebbi, Hosein
%Y Sarti, Gabriele
%Y Tutek, Martin
%S Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-476-7
%F grewal-2026-decodability
%X High probe accuracy does not by itself establish that a language model computes and uses the decoded value. We examine this inference in a syntax-sensitive arithmetic testbed: Llama-3.1-8B often fails multiplication when an operand is wrapped in parentheses or an additive identity. In the primary operand band, an input-only linear baseline nearly matches the original hidden-state probe’s regression R² \approx 0.96. A classical variance decomposition gives an analytical headroom of only 0.031 for this baseline class. In wider bands, selection-separated reanalysis instead finds positive activation advantages, which increase with regularization tuning; joint input-and-activation probes also improve over the baseline. These predictive gains are distinct from exact integer recovery and causal use. In the primary band, tested answer-site steering and state transplants produce small average output shifts and no observed donor-answer emissions, whereas operand-site interventions produce large effects. Operand access is necessary, with a strong bottleneck at one attention layer. The causal tests do not cover the wider-band predictive gains. We advocate explicit input baselines, matched causal tests, and positive controls, with conclusions restricted to the distributions, representations, and interventions actually examined.
%U https://aclanthology.org/2026.blackboxnlp-1.14/
%P 201-219

Markdown (Informal)

[Decodability Is Not Computation: Examining Probing Claims](https://aclanthology.org/2026.blackboxnlp-1.14/) (Grewal, BlackboxNLP 2026)

• Decodability Is Not Computation: Examining Probing Claims (Grewal, BlackboxNLP 2026)

ACL

• Kabir Singh Grewal. 2026. Decodability Is Not Computation: Examining Probing Claims. In Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 201–219, Budapest, Hungary. Association for Computational Linguistics.