CLAug 25, 2025

Integrating gender inclusivity into large language models via instruction tuning

arXiv:2508.18466v15 citationsh-index: 2
Originality Synthesis-oriented
AI Analysis

It addresses gender bias in Polish LLMs, offering a systematic solution for more inclusive language generation, though it is incremental as it applies existing tuning methods to a specific linguistic context.

This study tackled gender bias in Polish large language models (LLMs) by tuning them with the IPIS dataset of gender-inclusive instructions, resulting in models that generate more balanced outputs.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes