In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning

Mykhailo Koshil; Matthias Feurer; Katharina Eggensperger

doi:10.18653/v1/2025.trl-1.15

In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning

Mykhailo Koshil, Matthias Feurer, Katharina Eggensperger

Correct Metadata for

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>.

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

With in-context learning foundation models like TabPFN excelling on small supervised tabular learning tasks, it has been argued that “boosted trees are not the best default choice when working with data in tables”. However, such foundation models are inherently black-box models that do not provide interpretable predictions. We introduce a novel learning task to train ICL models to act as a nearest neighbor algorithm, which enables intelligible inference and does not decrease performance empirically.

Anthology ID:: 2025.trl-1.15
Volume:: Proceedings of the 4th Table Representation Learning Workshop
Month:: July
Year:: 2025
Address:: Vienna, Austria
Editors:: Shuaichen Chang, Madelon Hulsebos, Qian Liu, Wenhu Chen, Huan Sun
Venues:: TRL | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 182–191
Language:
URL:: https://aclanthology.org/2025.trl-1.15/
DOI:: 10.18653/v1/2025.trl-1.15
Bibkey:
Cite (ACL):: Mykhailo Koshil, Matthias Feurer, and Katharina Eggensperger. 2025. In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning. In Proceedings of the 4th Table Representation Learning Workshop, pages 182–191, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning (Koshil et al., TRL 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.trl-1.15.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{koshil-etal-2025-context,
    title = "In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning",
    author = "Koshil, Mykhailo  and
      Feurer, Matthias  and
      Eggensperger, Katharina",
    editor = "Chang, Shuaichen  and
      Hulsebos, Madelon  and
      Liu, Qian  and
      Chen, Wenhu  and
      Sun, Huan",
    booktitle = "Proceedings of the 4th Table Representation Learning Workshop",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.trl-1.15/",
    doi = "10.18653/v1/2025.trl-1.15",
    pages = "182--191",
    ISBN = "979-8-89176-268-8",
    abstract = "With in-context learning foundation models like TabPFN excelling on small supervised tabular learning tasks, it has been argued that ``boosted trees are not the best default choice when working with data in tables''. However, such foundation models are inherently black-box models that do not provide interpretable predictions. We introduce a novel learning task to train ICL models to act as a nearest neighbor algorithm, which enables intelligible inference and does not decrease performance empirically."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koshil-etal-2025-context">
    <titleInfo>
        <title>In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mykhailo</namePart>
        <namePart type="family">Koshil</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthias</namePart>
        <namePart type="family">Feurer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Katharina</namePart>
        <namePart type="family">Eggensperger</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 4th Table Representation Learning Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Shuaichen</namePart>
            <namePart type="family">Chang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Madelon</namePart>
            <namePart type="family">Hulsebos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Qian</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Wenhu</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Huan</namePart>
            <namePart type="family">Sun</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-268-8</identifier>
    </relatedItem>
    <abstract>With in-context learning foundation models like TabPFN excelling on small supervised tabular learning tasks, it has been argued that “boosted trees are not the best default choice when working with data in tables”. However, such foundation models are inherently black-box models that do not provide interpretable predictions. We introduce a novel learning task to train ICL models to act as a nearest neighbor algorithm, which enables intelligible inference and does not decrease performance empirically.</abstract>
    <identifier type="citekey">koshil-etal-2025-context</identifier>
    <identifier type="doi">10.18653/v1/2025.trl-1.15</identifier>
    <location>
        <url>https://aclanthology.org/2025.trl-1.15/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>182</start>
            <end>191</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning
%A Koshil, Mykhailo
%A Feurer, Matthias
%A Eggensperger, Katharina
%Y Chang, Shuaichen
%Y Hulsebos, Madelon
%Y Liu, Qian
%Y Chen, Wenhu
%Y Sun, Huan
%S Proceedings of the 4th Table Representation Learning Workshop
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-268-8
%F koshil-etal-2025-context
%X With in-context learning foundation models like TabPFN excelling on small supervised tabular learning tasks, it has been argued that “boosted trees are not the best default choice when working with data in tables”. However, such foundation models are inherently black-box models that do not provide interpretable predictions. We introduce a novel learning task to train ICL models to act as a nearest neighbor algorithm, which enables intelligible inference and does not decrease performance empirically.
%R 10.18653/v1/2025.trl-1.15
%U https://aclanthology.org/2025.trl-1.15/
%U https://doi.org/10.18653/v1/2025.trl-1.15
%P 182-191

Download as File

Markdown (Informal)

[In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning](https://aclanthology.org/2025.trl-1.15/) (Koshil et al., TRL 2025)

In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning (Koshil et al., TRL 2025)

ACL

Mykhailo Koshil, Matthias Feurer, and Katharina Eggensperger. 2025. In-Context Learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning. In Proceedings of the 4th Table Representation Learning Workshop, pages 182–191, Vienna, Austria. Association for Computational Linguistics.