Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.18466 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909752795070464 |
|---|---|
| author | Wróblewska, Alina Żuk, Bartosz |
| author_facet | Wróblewska, Alina Żuk, Bartosz |
| contents | Imagine a language with masculine, feminine, and neuter grammatical genders, yet, due to historical and political conventions, masculine forms are predominantly used to refer to men, women and mixed-gender groups. This is the reality of contemporary Polish. A social consequence of this unfair linguistic system is that large language models (LLMs) trained on Polish texts inherit and reinforce this masculine bias, generating gender-imbalanced outputs. This study addresses this issue by tuning LLMs using the IPIS dataset, a collection of human-crafted gender-inclusive proofreading in Polish and Polish-to-English translation instructions. Grounded in a theoretical linguistic framework, we design a system prompt with explicit gender-inclusive guidelines for Polish. In our experiments, we IPIS-tune multilingual LLMs (Llama-8B, Mistral-7B and Mistral-Nemo) and Polish-specific LLMs (Bielik and PLLuM). Our approach aims to integrate gender inclusivity as an inherent feature of these models, offering a systematic solution to mitigate gender bias in Polish language generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18466 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Integrating gender inclusivity into large language models via instruction tuning Wróblewska, Alina Żuk, Bartosz Computation and Language Imagine a language with masculine, feminine, and neuter grammatical genders, yet, due to historical and political conventions, masculine forms are predominantly used to refer to men, women and mixed-gender groups. This is the reality of contemporary Polish. A social consequence of this unfair linguistic system is that large language models (LLMs) trained on Polish texts inherit and reinforce this masculine bias, generating gender-imbalanced outputs. This study addresses this issue by tuning LLMs using the IPIS dataset, a collection of human-crafted gender-inclusive proofreading in Polish and Polish-to-English translation instructions. Grounded in a theoretical linguistic framework, we design a system prompt with explicit gender-inclusive guidelines for Polish. In our experiments, we IPIS-tune multilingual LLMs (Llama-8B, Mistral-7B and Mistral-Nemo) and Polish-specific LLMs (Bielik and PLLuM). Our approach aims to integrate gender inclusivity as an inherent feature of these models, offering a systematic solution to mitigate gender bias in Polish language generation. |
| title | Integrating gender inclusivity into large language models via instruction tuning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.18466 |