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

Kód výsledku v 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>

Výsledek na webu

<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

—

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 18th International Natural Language Generation Conference

ISBN

979-8-89176-321-0

ISSN

—

e-ISSN

—

Počet stran výsledku

17

Strana od-do

148-164

Název nakladatele

Association for Computational Linguistics

Místo vydání

Kerrville, TX, USA

Místo konání akce

Hanoi, Vietnam

Datum konání akce

29. 10. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—