Prompt-Based Gender-Inclusive Polish-English Translation Using Bielik Large Language Model with Structured Output

Krzysztof Wróbel


Abstract
We present a simple yet effective approach to gender-inclusive PolishEnglish translation for the PolEval 2025 Task 2 shared task. Without any fine-tuning, our solution leverages the Bielik 11B v2.6 model with carefully engineered system prompts and structured output, achieving a chrF score of 84.03 and securing first place in the translation subtask. The approach demonstrates that prompt engineering with few-shot examples and structured output can effectively handle the complex task of generating and removing gender-inclusive forms with the inclusive asterisk notation in Polish text. Per-direction analysis reveals stronger performance on PLEN (chrF 88.24) compared to ENPL (chrF 79.88), highlighting the asymmetric difficulty of adding versus removing inclusive forms.
Anthology ID:
2025.poleval-main.8
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:
54–59
Language:
URL:
https://aclanthology.org/2025.poleval-main.8/
DOI:
Bibkey:
Cite (ACL):
Krzysztof Wróbel. 2025. Prompt-Based Gender-Inclusive Polish-English Translation Using Bielik Large Language Model with Structured Output. In Proceedings of the PolEval 2025 Workshop, pages 54–59, Warsaw. Institute of Computer Science PAS and Association for Computational Linguistics.
Cite (Informal):
Prompt-Based Gender-Inclusive Polish-English Translation Using Bielik Large Language Model with Structured Output (Wróbel, PolEval 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.poleval-main.8.pdf