Instruction fine-tuning using pragmatic layer

Adrianna Paszkowska


Abstract
The Polish language, like some Slavic and Romance languages, has a masculine-centric bias in its generic forms, leading to frequent use of masculine nouns when referring to women or mixed-gender groups. This presents a linguistic challenge for development of gender-inclusive technologies, addressed in PolEval task 2.This paper presents pragmatic instruction fine-tuning approach, using Low-Rank Adaptation (LoRA) on the pre-trained Polish PLT5 sequence-to-sequence model.
Anthology ID:
2025.poleval-main.9
Volume:
Proceedings of the PolEval 2025 Workshop
Month:
November
Year:
2025
Address:
Warsaw
Editors:
Łukasz Kobyliński, Alina Wróblewska, Maciej Ogrodniczuk
Venues:
PolEval | WS
SIG:
Publisher:
Institute of Computer Science PAS and Association for Computational Linguistics
Note:
Pages:
60–65
Language:
URL:
https://aclanthology.org/2025.poleval-main.9/
DOI:
Bibkey:
Cite (ACL):
Adrianna Paszkowska. 2025. Instruction fine-tuning using pragmatic layer. In Proceedings of the PolEval 2025 Workshop, pages 60–65, Warsaw. Institute of Computer Science PAS and Association for Computational Linguistics.
Cite (Informal):
Instruction fine-tuning using pragmatic layer (Paszkowska, PolEval 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.poleval-main.9.pdf