Survival-Guided Length Control for Efficient Diffusion Language Models

Ivan Kobyzev; Abbas Ghaddar; Yufei Cui

Survival-Guided Length Control for Efficient Diffusion Language Models

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the end-of-sequence token and propose a plug-in, training-free length predictor that can be added to any existing DLM. Across reasoning and code-generation benchmarks, survival-guided length decoding speeds up inference by up to 7× while preserving task accuracy. We further find that predicted lengths vary widely even within the same dataset, making model performance sensitive to the chosen length.

Anthology ID:: 2026.emnlp-main.17
Volume:: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: EMNLP
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 391–399
Language:
URL:: https://aclanthology.org/2026.emnlp-main.17/
DOI:
Bibkey:
Cite (ACL):: Ivan Kobyzev, Abbas Ghaddar, and Yufei Cui. 2026. Survival-Guided Length Control for Efficient Diffusion Language Models. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 391–399, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Survival-Guided Length Control for Efficient Diffusion Language Models (Kobyzev et al., EMNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.emnlp-main.17.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{kobyzev-etal-2026-survival,
    title = "Survival-Guided Length Control for Efficient Diffusion Language Models",
    author = "Kobyzev, Ivan  and
      Ghaddar, Abbas  and
      Cui, Yufei",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.17/",
    pages = "391--399",
    ISBN = "979-8-89176-459-0",
    abstract = "Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the end-of-sequence token and propose a plug-in, training-free length predictor that can be added to any existing DLM. Across reasoning and code-generation benchmarks, survival-guided length decoding speeds up inference by up to $7\times$ while preserving task accuracy. We further find that predicted lengths vary widely even within the same dataset, making model performance sensitive to the chosen length."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kobyzev-etal-2026-survival">
    <titleInfo>
        <title>Survival-Guided Length Control for Efficient Diffusion Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Kobyzev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abbas</namePart>
        <namePart type="family">Ghaddar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yufei</namePart>
        <namePart type="family">Cui</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 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the end-of-sequence token and propose a plug-in, training-free length predictor that can be added to any existing DLM. Across reasoning and code-generation benchmarks, survival-guided length decoding speeds up inference by up to 7\times while preserving task accuracy. We further find that predicted lengths vary widely even within the same dataset, making model performance sensitive to the chosen length.</abstract>
    <identifier type="citekey">kobyzev-etal-2026-survival</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.17/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>391</start>
            <end>399</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Survival-Guided Length Control for Efficient Diffusion Language Models
%A Kobyzev, Ivan
%A Ghaddar, Abbas
%A Cui, Yufei
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F kobyzev-etal-2026-survival
%X Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the end-of-sequence token and propose a plug-in, training-free length predictor that can be added to any existing DLM. Across reasoning and code-generation benchmarks, survival-guided length decoding speeds up inference by up to 7\times while preserving task accuracy. We further find that predicted lengths vary widely even within the same dataset, making model performance sensitive to the chosen length.
%U https://aclanthology.org/2026.emnlp-main.17/
%P 391-399

Download as File

Markdown (Informal)

[Survival-Guided Length Control for Efficient Diffusion Language Models](https://aclanthology.org/2026.emnlp-main.17/) (Kobyzev et al., EMNLP 2026)

Survival-Guided Length Control for Efficient Diffusion Language Models (Kobyzev et al., EMNLP 2026)

ACL

Ivan Kobyzev, Abbas Ghaddar, and Yufei Cui. 2026. Survival-Guided Length Control for Efficient Diffusion Language Models. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 391–399, Budapest, Hungary. Association for Computational Linguistics.