Towards Achieving Concept Completeness for Textual Concept Bottleneck Models

Milan Bhan; Yann Choho; Jean-Noël Vittaut; Nicolas Chesneau; Pierre Moreau; Marie-Jeanne Lesot

doi:10.18653/v1/2025.findings-emnlp.106

Towards Achieving Concept Completeness for Textual Concept Bottleneck Models

Milan Bhan, Yann Choho, Jean-Noël Vittaut, Nicolas Chesneau, Pierre Moreau, Marie-Jeanne Lesot

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

This paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking results against competitors in terms of concept basis completeness and concept detection accuracy, offering a promising solution to reliably enhance interpretability of NLP classifiers.

Anthology ID:: 2025.findings-emnlp.106
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2025
Month:: November
Year:: 2025
Address:: Suzhou, China
Editors:: Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 2007–2024
Language:
URL:: https://aclanthology.org/2025.findings-emnlp.106/
DOI:: 10.18653/v1/2025.findings-emnlp.106
Bibkey:
Cite (ACL):: Milan Bhan, Yann Choho, Jean-Noël Vittaut, Nicolas Chesneau, Pierre Moreau, and Marie-Jeanne Lesot. 2025. Towards Achieving Concept Completeness for Textual Concept Bottleneck Models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 2007–2024, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):: Towards Achieving Concept Completeness for Textual Concept Bottleneck Models (Bhan et al., Findings 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.findings-emnlp.106.pdf
Checklist:: 2025.findings-emnlp.106.checklist.pdf

PDF Cite Search Checklist Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{bhan-etal-2025-towards,
    title = "Towards Achieving Concept Completeness for Textual Concept Bottleneck Models",
    author = {Bhan, Milan  and
      Choho, Yann  and
      Vittaut, Jean-No{\"e}l  and
      Chesneau, Nicolas  and
      Moreau, Pierre  and
      Lesot, Marie-Jeanne},
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.106/",
    doi = "10.18653/v1/2025.findings-emnlp.106",
    pages = "2007--2024",
    ISBN = "979-8-89176-335-7",
    abstract = "This paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking results against competitors in terms of concept basis completeness and concept detection accuracy, offering a promising solution to reliably enhance interpretability of NLP classifiers."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhan-etal-2025-towards">
    <titleInfo>
        <title>Towards Achieving Concept Completeness for Textual Concept Bottleneck Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Milan</namePart>
        <namePart type="family">Bhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yann</namePart>
        <namePart type="family">Choho</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean-Noël</namePart>
        <namePart type="family">Vittaut</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicolas</namePart>
        <namePart type="family">Chesneau</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pierre</namePart>
        <namePart type="family">Moreau</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marie-Jeanne</namePart>
        <namePart type="family">Lesot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>This paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking results against competitors in terms of concept basis completeness and concept detection accuracy, offering a promising solution to reliably enhance interpretability of NLP classifiers.</abstract>
    <identifier type="citekey">bhan-etal-2025-towards</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-emnlp.106</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.106/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>2007</start>
            <end>2024</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Towards Achieving Concept Completeness for Textual Concept Bottleneck Models
%A Bhan, Milan
%A Choho, Yann
%A Vittaut, Jean-Noël
%A Chesneau, Nicolas
%A Moreau, Pierre
%A Lesot, Marie-Jeanne
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F bhan-etal-2025-towards
%X This paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking results against competitors in terms of concept basis completeness and concept detection accuracy, offering a promising solution to reliably enhance interpretability of NLP classifiers.
%R 10.18653/v1/2025.findings-emnlp.106
%U https://aclanthology.org/2025.findings-emnlp.106/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.106
%P 2007-2024

Download as File

Markdown (Informal)

[Towards Achieving Concept Completeness for Textual Concept Bottleneck Models](https://aclanthology.org/2025.findings-emnlp.106/) (Bhan et al., Findings 2025)

Towards Achieving Concept Completeness for Textual Concept Bottleneck Models (Bhan et al., Findings 2025)

ACL

Milan Bhan, Yann Choho, Jean-Noël Vittaut, Nicolas Chesneau, Pierre Moreau, and Marie-Jeanne Lesot. 2025. Towards Achieving Concept Completeness for Textual Concept Bottleneck Models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 2007–2024, Suzhou, China. Association for Computational Linguistics.