Hypernetworks for Perspectivist Adaptation

Daniil Ignatev; Denis Paperno; Massimo Poesio

Hypernetworks for Perspectivist Adaptation

Daniil Ignatev, Denis Paperno, Massimo Poesio

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

The task of perspective-aware classification introduces a bottleneck in terms of parametric efficiency that did not get enough recognition in existing studies. In this article, we aim to address this issue by applying an existing architecture, the hypernetwork+adapters combination, to perspectivist classification. Ultimately, we arrive at a solution that can compete with specialized models in adopting user perspectives on hate speech and toxicity detection, while also making use of considerably fewer parameters. Our solution is architecture-agnostic and can be applied to a wide range of base models out of the box.

Anthology ID:: 2025.nlperspectives-1.10
Volume:: Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP
Month:: November
Year:: 2025
Address:: Suzhou, China
Editors:: Gavin Abercrombie, Valerio Basile, Simona Frenda, Sara Tonelli, Shiran Dudy
Venues:: NLPerspectives | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 111–122
Language:
URL:: https://aclanthology.org/2025.nlperspectives-1.10/
DOI:
Bibkey:
Cite (ACL):: Daniil Ignatev, Denis Paperno, and Massimo Poesio. 2025. Hypernetworks for Perspectivist Adaptation. In Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP, pages 111–122, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):: Hypernetworks for Perspectivist Adaptation (Ignatev et al., NLPerspectives 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.nlperspectives-1.10.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{ignatev-etal-2025-hypernetworks,
    title = "Hypernetworks for Perspectivist Adaptation",
    author = "Ignatev, Daniil  and
      Paperno, Denis  and
      Poesio, Massimo",
    editor = "Abercrombie, Gavin  and
      Basile, Valerio  and
      Frenda, Simona  and
      Tonelli, Sara  and
      Dudy, Shiran",
    booktitle = "Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.nlperspectives-1.10/",
    pages = "111--122",
    ISBN = "979-8-89176-350-0",
    abstract = "The task of perspective-aware classification introduces a bottleneck in terms of parametric efficiency that did not get enough recognition in existing studies. In this article, we aim to address this issue by applying an existing architecture, the hypernetwork+adapters combination, to perspectivist classification. Ultimately, we arrive at a solution that can compete with specialized models in adopting user perspectives on hate speech and toxicity detection, while also making use of considerably fewer parameters. Our solution is architecture-agnostic and can be applied to a wide range of base models out of the box."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ignatev-etal-2025-hypernetworks">
    <titleInfo>
        <title>Hypernetworks for Perspectivist Adaptation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daniil</namePart>
        <namePart type="family">Ignatev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Denis</namePart>
        <namePart type="family">Paperno</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Massimo</namePart>
        <namePart type="family">Poesio</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>Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Gavin</namePart>
            <namePart type="family">Abercrombie</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Valerio</namePart>
            <namePart type="family">Basile</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simona</namePart>
            <namePart type="family">Frenda</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Tonelli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shiran</namePart>
            <namePart type="family">Dudy</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">979-8-89176-350-0</identifier>
    </relatedItem>
    <abstract>The task of perspective-aware classification introduces a bottleneck in terms of parametric efficiency that did not get enough recognition in existing studies. In this article, we aim to address this issue by applying an existing architecture, the hypernetwork+adapters combination, to perspectivist classification. Ultimately, we arrive at a solution that can compete with specialized models in adopting user perspectives on hate speech and toxicity detection, while also making use of considerably fewer parameters. Our solution is architecture-agnostic and can be applied to a wide range of base models out of the box.</abstract>
    <identifier type="citekey">ignatev-etal-2025-hypernetworks</identifier>
    <location>
        <url>https://aclanthology.org/2025.nlperspectives-1.10/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>111</start>
            <end>122</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Hypernetworks for Perspectivist Adaptation
%A Ignatev, Daniil
%A Paperno, Denis
%A Poesio, Massimo
%Y Abercrombie, Gavin
%Y Basile, Valerio
%Y Frenda, Simona
%Y Tonelli, Sara
%Y Dudy, Shiran
%S Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-350-0
%F ignatev-etal-2025-hypernetworks
%X The task of perspective-aware classification introduces a bottleneck in terms of parametric efficiency that did not get enough recognition in existing studies. In this article, we aim to address this issue by applying an existing architecture, the hypernetwork+adapters combination, to perspectivist classification. Ultimately, we arrive at a solution that can compete with specialized models in adopting user perspectives on hate speech and toxicity detection, while also making use of considerably fewer parameters. Our solution is architecture-agnostic and can be applied to a wide range of base models out of the box.
%U https://aclanthology.org/2025.nlperspectives-1.10/
%P 111-122

Download as File

Markdown (Informal)

[Hypernetworks for Perspectivist Adaptation](https://aclanthology.org/2025.nlperspectives-1.10/) (Ignatev et al., NLPerspectives 2025)

Hypernetworks for Perspectivist Adaptation (Ignatev et al., NLPerspectives 2025)

ACL

Daniil Ignatev, Denis Paperno, and Massimo Poesio. 2025. Hypernetworks for Perspectivist Adaptation. In Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP, pages 111–122, Suzhou, China. Association for Computational Linguistics.