Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control

James A. Michaelov; Carmen Amo Alonso; Tyler A. Chang; Roger Levy

Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control

James A. Michaelov, Carmen Amo Alonso, Tyler A. Chang, Roger P. Levy

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

Ensuring that multilingual language models generate coherent text in a specific target language is a major issue in multilingual language modeling. We develop an optimal control method for target-language text generation as well as a framework for evaluating the quality of generated text in terms of language adherence, linguistic coherence, and semantic coherence. We find that the proposed method performs at least as well as the prominent difference-in-means activation steering method for the majority of models tested, with substantially less hyperparameter tuning required.

Anthology ID:: 2026.emnlp-main.551
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:: 12644–12664
Language:
URL:: https://aclanthology.org/2026.emnlp-main.551/
DOI:
Bibkey:
Cite (ACL):: James A. Michaelov, Carmen Amo Alonso, Tyler A. Chang, and Roger P. Levy. 2026. Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 12644–12664, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control (Michaelov et al., EMNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.emnlp-main.551.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{michaelov-etal-2026-target,
    title = "Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control",
    author = "Michaelov, James A.  and
      Alonso, Carmen Amo  and
      Chang, Tyler A.  and
      Levy, Roger P.",
    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.551/",
    pages = "12644--12664",
    ISBN = "979-8-89176-459-0",
    abstract = "Ensuring that multilingual language models generate coherent text in a specific target language is a major issue in multilingual language modeling. We develop an optimal control method for target-language text generation as well as a framework for evaluating the quality of generated text in terms of language adherence, linguistic coherence, and semantic coherence. We find that the proposed method performs at least as well as the prominent difference-in-means activation steering method for the majority of models tested, with substantially less hyperparameter tuning required."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="michaelov-etal-2026-target">
    <titleInfo>
        <title>Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Michaelov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carmen</namePart>
        <namePart type="given">Amo</namePart>
        <namePart type="family">Alonso</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tyler</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roger</namePart>
        <namePart type="given">P</namePart>
        <namePart type="family">Levy</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>Ensuring that multilingual language models generate coherent text in a specific target language is a major issue in multilingual language modeling. We develop an optimal control method for target-language text generation as well as a framework for evaluating the quality of generated text in terms of language adherence, linguistic coherence, and semantic coherence. We find that the proposed method performs at least as well as the prominent difference-in-means activation steering method for the majority of models tested, with substantially less hyperparameter tuning required.</abstract>
    <identifier type="citekey">michaelov-etal-2026-target</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.551/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>12644</start>
            <end>12664</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control
%A Michaelov, James A.
%A Alonso, Carmen Amo
%A Chang, Tyler A.
%A Levy, Roger P.
%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 michaelov-etal-2026-target
%X Ensuring that multilingual language models generate coherent text in a specific target language is a major issue in multilingual language modeling. We develop an optimal control method for target-language text generation as well as a framework for evaluating the quality of generated text in terms of language adherence, linguistic coherence, and semantic coherence. We find that the proposed method performs at least as well as the prominent difference-in-means activation steering method for the majority of models tested, with substantially less hyperparameter tuning required.
%U https://aclanthology.org/2026.emnlp-main.551/
%P 12644-12664

Download as File

Markdown (Informal)

[Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control](https://aclanthology.org/2026.emnlp-main.551/) (Michaelov et al., EMNLP 2026)

Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control (Michaelov et al., EMNLP 2026)

ACL

James A. Michaelov, Carmen Amo Alonso, Tyler A. Chang, and Roger P. Levy. 2026. Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 12644–12664, Budapest, Hungary. Association for Computational Linguistics.