<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="asada-miwa-2026-principled">
    <titleInfo>
        <title>Principled Self-Correction in Discrete Diffusion: A UCB-Guided Framework for Text Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Masaki</namePart>
        <namePart type="family">Asada</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Makoto</namePart>
        <namePart type="family">Miwa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-380-7</identifier>
    </relatedItem>
    <abstract>Inspired by their success in image synthesis, diffusion models offer a flexible, iterative alternative to rigid left-to-right text generation. However, a fundamental training-inference discrepancy hinders their performance: models are trained on corrupted ground-truth tokens, but at inference time they must denoise inputs corrupted from their own predictions. To bridge this gap, we propose a unified framework. First, Deeper Self-Prediction (DSP) is a multi-step training objective that teaches robust self-correction by forcing the model to denoise its own intermediate outputs. Second, UCB-guided Decoding is a principled inference algorithm that frames token re-masking as a multi-armed bandit problem, using the Upper Confidence Bound (UCB) to balance exploration and exploitation. Experiments on text generation tasks demonstrate consistent improvements over existing diffusion baselines. The framework achieves higher faithfulness and coherence according to both automatic metrics and LLM-as-a-Judge evaluations.</abstract>
    <identifier type="citekey">asada-miwa-2026-principled</identifier>
    <location>
        <url>https://aclanthology.org/2026.eacl-long.314/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>6678</start>
            <end>6692</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Principled Self-Correction in Discrete Diffusion: A UCB-Guided Framework for Text Generation
%A Asada, Masaki
%A Miwa, Makoto
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F asada-miwa-2026-principled
%X Inspired by their success in image synthesis, diffusion models offer a flexible, iterative alternative to rigid left-to-right text generation. However, a fundamental training-inference discrepancy hinders their performance: models are trained on corrupted ground-truth tokens, but at inference time they must denoise inputs corrupted from their own predictions. To bridge this gap, we propose a unified framework. First, Deeper Self-Prediction (DSP) is a multi-step training objective that teaches robust self-correction by forcing the model to denoise its own intermediate outputs. Second, UCB-guided Decoding is a principled inference algorithm that frames token re-masking as a multi-armed bandit problem, using the Upper Confidence Bound (UCB) to balance exploration and exploitation. Experiments on text generation tasks demonstrate consistent improvements over existing diffusion baselines. The framework achieves higher faithfulness and coherence according to both automatic metrics and LLM-as-a-Judge evaluations.
%U https://aclanthology.org/2026.eacl-long.314/
%P 6678-6692

Markdown (Informal)

[Principled Self-Correction in Discrete Diffusion: A UCB-Guided Framework for Text Generation](https://aclanthology.org/2026.eacl-long.314/) (Asada & Miwa, EACL 2026)

• Principled Self-Correction in Discrete Diffusion: A UCB-Guided Framework for Text Generation (Asada & Miwa, EACL 2026)

ACL

• Masaki Asada and Makoto Miwa. 2026. Principled Self-Correction in Discrete Diffusion: A UCB-Guided Framework for Text Generation. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6678–6692, Rabat, Morocco. Association for Computational Linguistics.