How Gender Interacts with Political Values: A Case Study on Czech BERT Models

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492840" target="_blank" >RIV/00216208:11320/24:10492840 - isvavai.cz</a>

Alternative codes found

RIV/00216208:11320/25:WP4KZUSQ

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

How Gender Interacts with Political Values: A Case Study on Czech BERT Models

Original language description

Neural language models, which reach state-of-the-art results on most natural language processing tasks, are trained on large text corpora that inevitably contain value-burdened content and often capture undesirable biases, which the models reflect. This case study focuses on the political biases of pre-trained encoders in Czech and compares them with a representative value survey. Because Czech is a gendered language, we also measure how the grammatical gender coincides with responses to men and women in the survey. We introduce a novel method for measuring the model&apos;s perceived political values. We find that the models do not assign statement probability following value-driven reasoning, and there is no systematic difference between feminine and masculine sentences. We conclude that BERT-sized models do not manifest systematic alignment with political values and that the biases observed in the models are rather due to superficial imitation of training data patterns than systematic value beliefs encod

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

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2024

Confidentiality

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

Article name in the collection

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

ISBN

978-2-493-81410-4

ISSN

2522-2686

e-ISSN

—

Number of pages

8

Pages from-to

3038-3045

Publisher name

European Language Resources Association

Place of publication

Torino, Italy

Event location

Torino, Italy

Event date

May 22, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—