The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models

Shihui Li; Mette Friis Andersen; Martha Lewis

The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models

Shihui Li, Mette Friis Andersen, Martha Lewis

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

Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled. We use mechanistic interpretability techniques to identify causal subspaces in a range of LLMs covering different architectures and sizes. We show that we are able to steer output on classification tasks across different parts of speech. We are also able to steer output on generation tasks, indicating that these techniques can be used to control the metaphoricity of LLM output.

Anthology ID:: 2026.blackboxnlp-1.54
Volume:: Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Dana Arad, Yonatan Belinkov, Hanjie Chen, Nils Feldhus, Aaron Mueller, Hosein Mohebbi, Gabriele Sarti, Martin Tutek
Venues:: BlackboxNLP | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 965–985
Language:
URL:: https://aclanthology.org/2026.blackboxnlp-1.54/
DOI:
Bibkey:
Cite (ACL):: Shihui Li, Mette Friis Andersen, and Martha Lewis. 2026. The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models. In Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 965–985, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models (Li et al., BlackboxNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.blackboxnlp-1.54.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{li-etal-2026-geometry,
    title = "The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models",
    author = "Li, Shihui  and
      Andersen, Mette Friis  and
      Lewis, Martha",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.54/",
    pages = "965--985",
    ISBN = "979-8-89176-476-7",
    abstract = "Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled. We use mechanistic interpretability techniques to identify causal subspaces in a range of LLMs covering different architectures and sizes. We show that we are able to steer output on classification tasks across different parts of speech. We are also able to steer output on generation tasks, indicating that these techniques can be used to control the metaphoricity of LLM output."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-geometry">
    <titleInfo>
        <title>The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shihui</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mette</namePart>
        <namePart type="given">Friis</namePart>
        <namePart type="family">Andersen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Martha</namePart>
        <namePart type="family">Lewis</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>Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled. We use mechanistic interpretability techniques to identify causal subspaces in a range of LLMs covering different architectures and sizes. We show that we are able to steer output on classification tasks across different parts of speech. We are also able to steer output on generation tasks, indicating that these techniques can be used to control the metaphoricity of LLM output.</abstract>
    <identifier type="citekey">li-etal-2026-geometry</identifier>
    <location>
        <url>https://aclanthology.org/2026.blackboxnlp-1.54/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>965</start>
            <end>985</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models
%A Li, Shihui
%A Andersen, Mette Friis
%A Lewis, Martha
%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 li-etal-2026-geometry
%X Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled. We use mechanistic interpretability techniques to identify causal subspaces in a range of LLMs covering different architectures and sizes. We show that we are able to steer output on classification tasks across different parts of speech. We are also able to steer output on generation tasks, indicating that these techniques can be used to control the metaphoricity of LLM output.
%U https://aclanthology.org/2026.blackboxnlp-1.54/
%P 965-985

Download as File

Markdown (Informal)

[The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models](https://aclanthology.org/2026.blackboxnlp-1.54/) (Li et al., BlackboxNLP 2026)

The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models (Li et al., BlackboxNLP 2026)

ACL

Shihui Li, Mette Friis Andersen, and Martha Lewis. 2026. The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models. In Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 965–985, Budapest, Hungary. Association for Computational Linguistics.