<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jacopin-2026-present">
    <titleInfo>
        <title>Present but Barely Used: Reproducing the Emergent Othello World Model in a Masked Diffusion Language Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Éric</namePart>
        <namePart type="family">Jacopin</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>Autoregressive (AR) sequence models trained only to predict legal Othello moves develop an emergent, linearly-decodable representation of the board in a player-relative (MINE/YOURS) frame (Li et al., 2023; Nanda et al., 2023). We ask whether this emergent linear world model survives a change of training objective: from next-token prediction to masked diffusion (Sahoo et al., 2024). On an identical GPT-2 backbone and identical data, we train an AR control and a masked diffusion language model (MDLM), reproduce the Li–Nanda linear/relative dissociation on the control, and probe the MDLM with the same battery. We find that the linear player-relative world model transfers to masked diffusion (the dissociation reproduces) but is substantially weaker (~0.79 vs. the AR’s 0.96 two-way accuracy). A Nanda-style causal intervention shows the representation is only minimally used: a statistically real but tiny and inconsistent effect (mean +0.02, 24% win-rate) against the AR’s strong, consistent +0.21 / 84%. Order-artifact controls confirm the representation is genuine rather than an artifact of an easy unmasking order. As a reproducibility contribution, this is a generalizability stress test of the Li–Nanda finding under a change of training objective, anchored throughout by random-weight and shuffled-label control tasks and by component ablations. We report a second implementation, in Rust on an independent interpretability stack, that reproduces our headline numbers. Code, data recipes, and model checkpoints are available anonymously for review at https://anonymous.4open.science/r/othello-mdlm-anon-DBC2/.</abstract>
    <identifier type="citekey">jacopin-2026-present</identifier>
    <location>
        <url>https://aclanthology.org/2026.blackboxnlp-1.56/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1007</start>
            <end>1016</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Present but Barely Used: Reproducing the Emergent Othello World Model in a Masked Diffusion Language Model
%A Jacopin, Éric
%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 jacopin-2026-present
%X Autoregressive (AR) sequence models trained only to predict legal Othello moves develop an emergent, linearly-decodable representation of the board in a player-relative (MINE/YOURS) frame (Li et al., 2023; Nanda et al., 2023). We ask whether this emergent linear world model survives a change of training objective: from next-token prediction to masked diffusion (Sahoo et al., 2024). On an identical GPT-2 backbone and identical data, we train an AR control and a masked diffusion language model (MDLM), reproduce the Li–Nanda linear/relative dissociation on the control, and probe the MDLM with the same battery. We find that the linear player-relative world model transfers to masked diffusion (the dissociation reproduces) but is substantially weaker (~0.79 vs. the AR’s 0.96 two-way accuracy). A Nanda-style causal intervention shows the representation is only minimally used: a statistically real but tiny and inconsistent effect (mean +0.02, 24% win-rate) against the AR’s strong, consistent +0.21 / 84%. Order-artifact controls confirm the representation is genuine rather than an artifact of an easy unmasking order. As a reproducibility contribution, this is a generalizability stress test of the Li–Nanda finding under a change of training objective, anchored throughout by random-weight and shuffled-label control tasks and by component ablations. We report a second implementation, in Rust on an independent interpretability stack, that reproduces our headline numbers. Code, data recipes, and model checkpoints are available anonymously for review at https://anonymous.4open.science/r/othello-mdlm-anon-DBC2/.
%U https://aclanthology.org/2026.blackboxnlp-1.56/
%P 1007-1016

Markdown (Informal)

[Present but Barely Used: Reproducing the Emergent Othello World Model in a Masked Diffusion Language Model](https://aclanthology.org/2026.blackboxnlp-1.56/) (Jacopin, BlackboxNLP 2026)

• Present but Barely Used: Reproducing the Emergent Othello World Model in a Masked Diffusion Language Model (Jacopin, BlackboxNLP 2026)

ACL

• Éric Jacopin. 2026. Present but Barely Used: Reproducing the Emergent Othello World Model in a Masked Diffusion Language Model. In Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 1007–1016, Budapest, Hungary. Association for Computational Linguistics.