Prompting encoder models for zero-shot classification: a cross-domain study in Italian.

Addressing the challenge of limited annotated data in specialized fields and low-resource languages is crucial for the effective use of language models (LMs). While most large language models (LLMs) are trained on general-purpose English corpora, there is a notable gap in models specifically tailore...

Descripción completa

Detalles Bibliográficos
Publicado en:Language Resources & Evaluation Vol. 59; no. 4; pp. 3659 - 3698
Autores principales: Auriemma, Serena, Miliani, Martina, Madeddu, Mauro, Bondielli, Alessandro, Passaro, Lucia, Lenci, Alessandro
Formato: Artículo
Publicado: Springer Nature Dec2025
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=189912025&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 189912025
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        1574020X
        179V
      jtl: Language Resources & Evaluation
      issn: 1574020X
      maglogo: N
    pubinfo:
      dt: Dec2025
      vid: 59
      iid: 4
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        189912025
        10.1007/s10579-025-09853-0
      ppf: 3659
      ppct: 39
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 1.1MB
      tig:
        atl: Prompting encoder models for zero-shot classification: a cross-domain study in Italian.
      aug:
        au:
          Auriemma, Serena
          Miliani, Martina
          Madeddu, Mauro
          Bondielli, Alessandro
          Passaro, Lucia
          Lenci, Alessandro
        affil:
          https://ror.org/03ad39j10 CoLing Lab, Department of Philology, Literature and Linguistics, University of Pisa, 36 Santa Maria Street, 56126, Pisa, Italy
          https://ror.org/03ad39j10 Department of Computer Science, University of Pisa, 3 Largo Bruno Pontecorvo, 56127, Pisa, Italy
      su:
        Italian language
        Domain specificity
        Jargon (Terminology)
        Machine learning
        Natural language processing
        Feature extraction
        Language models
        Classification
      sug:
        subj:
          Italian language
          Domain specificity
          Jargon (Terminology)
          Machine learning
          Natural language processing
          Feature extraction
          Language models
          Classification
      keyword:
        Communication and Culture Linguistics
        Domain-adapted model
        Encoder
        Language
        Legal
        Prompting
        Public administration
        Zero-shot classification
      ab: Addressing the challenge of limited annotated data in specialized fields and low-resource languages is crucial for the effective use of language models (LMs). While most large language models (LLMs) are trained on general-purpose English corpora, there is a notable gap in models specifically tailored for Italian, particularly for technical and bureaucratic jargon. This paper explores the feasibility of employing smaller, domain-specific encoder LMs alongside prompting techniques to enhance performance in these specialized contexts. Our study concentrates on the Italian bureaucratic and legal language, experimenting with both general-purpose and further pre-trained encoder-only models. We evaluated the models on downstream tasks such as document classification and entity typing and conducted intrinsic evaluations using Pseudo-log-likelihood. The results indicate that while further pre-trained models may show diminished robustness in general knowledge, they exhibit superior adaptability for domain-specific tasks, even in a zero-shot setting. Furthermore, the application of calibration techniques and in-domain verbalizers significantly enhances the efficacy of encoder models. These domain-specialized models prove to be particularly advantageous in scenarios where in-domain resources or expertise are scarce. In conclusion, our findings offer new insights into the use of Italian models in specialized contexts, which may have a significant impact on both research and industrial applications in the digital transformation era.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Language Resources & Evaluation is a copyright of Springer, 2025. All Rights Reserved.
      item: Language Resources & Evaluation
      holder: Springer Nature
      dt:
        @attributes:
          year: 2025
    holdings:
      @attributes:
        islocal: N