Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511619" target="_blank" >RIV/00216208:11320/25:10511619 - isvavai.cz</a>

Result on the web

<a href="https://ufal.mff.cuni.cz/~odusek/inlg2025/inlg2025-main/pdf/2025.inlg-main.10.pdf" target="_blank" >https://ufal.mff.cuni.cz/~odusek/inlg2025/inlg2025-main/pdf/2025.inlg-main.10.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation

Original language description

Mitigation of biases, such as language models&apos; reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The crucial aspect of debiasing is to ensure that the models preserve their versatile capabilities, including their ability to solve language tasks and equitably represent various genders. To address these issues, we introduce Dual Debiasing Algorithm through Model Adaptation (2DAMA). Novel Dual Debiasing enables robust reduction of stereotypical bias while preserving desired factual gender information encoded by language models. We show that 2DAMA effectively reduces gender bias in language models for English and is one of the first approaches facilitating the mitigation of their stereotypical tendencies in translation. The proposed method’s key advantage is the preservation of factual gender cues, which are useful in a wide range of natural language processing tasks.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 18th International Natural Language Generation Conference

ISBN

979-8-89176-321-0

ISSN

—

e-ISSN

—

Number of pages

17

Pages from-to

148-164

Publisher name

Association for Computational Linguistics

Place of publication

Kerrville, TX, USA

Event location

Hanoi, Vietnam

Event date

Oct 29, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—