<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferrazzi-etal-2026-decselfmask">
    <titleInfo>
        <title>DecSelfMask: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pietro</namePart>
        <namePart type="family">Ferrazzi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matteo</namePart>
        <namePart type="family">Merler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Giovanni</namePart>
        <namePart type="family">Bonetta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alberto</namePart>
        <namePart type="family">Lavelli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bernardo</namePart>
        <namePart type="family">Magnini</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>Classification tasks require annotated data, which can often be expensive, time-consuming, or even unfeasible to collect.This is the case of the medical domain, where large datasets often have few annotated examples. To address this, we propose DecSelfMask (Decoder Self-learning by Masking), an approach to enhance decoder-only performance on classification tasks. We build on common self-learning approaches by leveraging a model to create training examples from unlabeled data, and propose a novel relevance-guided masking strategy.We use relevance attribution methods to determine what portions of unannotated texts are relevant for a task. We then create self-supervised training examples by masking out those portions, training the model to reconstruct them via next-token-prediction. We hypothesize that those examples convey knowledge about the structure and semantics of unannotated data that can be useful for downstream performance. We test our approach on 136 tasks from a collection of 1.9M clinical notes from an Italian hospital. We quantify DecSelfMask’s impact on downstream tasks on 5 models of different scales and families, including a probing analysis. Experiments show consistent gains, outperforming the base models (+9.1 points in Macro F1), continual pretraining (+6.3), synthetic label generation (+12.5), as well as common baselines. The results show that relevance attribution can serve as a powerful source of supervision for decoder learning from unlabeled data, beyond existing methods.</abstract>
    <identifier type="citekey">ferrazzi-etal-2026-decselfmask</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1372/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>31311</start>
            <end>31327</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DecSelfMask: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification
%A Ferrazzi, Pietro
%A Merler, Matteo
%A Bonetta, Giovanni
%A Lavelli, Alberto
%A Magnini, Bernardo
%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 ferrazzi-etal-2026-decselfmask
%X Classification tasks require annotated data, which can often be expensive, time-consuming, or even unfeasible to collect.This is the case of the medical domain, where large datasets often have few annotated examples. To address this, we propose DecSelfMask (Decoder Self-learning by Masking), an approach to enhance decoder-only performance on classification tasks. We build on common self-learning approaches by leveraging a model to create training examples from unlabeled data, and propose a novel relevance-guided masking strategy.We use relevance attribution methods to determine what portions of unannotated texts are relevant for a task. We then create self-supervised training examples by masking out those portions, training the model to reconstruct them via next-token-prediction. We hypothesize that those examples convey knowledge about the structure and semantics of unannotated data that can be useful for downstream performance. We test our approach on 136 tasks from a collection of 1.9M clinical notes from an Italian hospital. We quantify DecSelfMask’s impact on downstream tasks on 5 models of different scales and families, including a probing analysis. Experiments show consistent gains, outperforming the base models (+9.1 points in Macro F1), continual pretraining (+6.3), synthetic label generation (+12.5), as well as common baselines. The results show that relevance attribution can serve as a powerful source of supervision for decoder learning from unlabeled data, beyond existing methods.
%U https://aclanthology.org/2026.emnlp-main.1372/
%P 31311-31327

Markdown (Informal)

[DecSelfMask: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification](https://aclanthology.org/2026.emnlp-main.1372/) (Ferrazzi et al., EMNLP 2026)

• DecSelfMask: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification (Ferrazzi et al., EMNLP 2026)

ACL

• Pietro Ferrazzi, Matteo Merler, Giovanni Bonetta, Alberto Lavelli, and Bernardo Magnini. 2026. DecSelfMask: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 31311–31327, Budapest, Hungary. Association for Computational Linguistics.