View in EDS

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

Saved in:
Bibliographic Details
Title: Prompting encoder models for zero-shot classification: a cross-domain study in Italian.
Authors: Auriemma, Serena1 (AUTHOR) serena.auriemma@phd.unipi.it, Miliani, Martina1 (AUTHOR) martina.miliani@fileli.unipi.it, Madeddu, Mauro2 (AUTHOR) mauro.madeddu@phd.unipi.it, Bondielli, Alessandro1,2 (AUTHOR) alessandro.bondielli@unipi.it, Passaro, Lucia2 (AUTHOR) lucia.passaro@unipi.it, Lenci, Alessandro1 (AUTHOR) alessandro.lenci@unipi.it
Source: Language Resources & Evaluation. Dec2025, Vol. 59 Issue 4, p3659-3697. 39p.
Subjects: Italian language, Domain specificity, Jargon (Terminology), Machine learning, Natural language processing, Feature extraction, Language models, Classification
Abstract: 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. [ABSTRACT FROM AUTHOR]
Copyright of Language Resources & Evaluation is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract: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. [ABSTRACT FROM AUTHOR]
ISSN:1574020X
DOI:10.1007/s10579-025-09853-0