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

Kód výsledku v 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>

Nalezeny alternativní kódy

RIV/00216208:11320/25:WP4KZUSQ

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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

Název v anglickém jazyce

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

Popis výsledku anglicky

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

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

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

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

—

Počet stran výsledku

8

Strana od-do

3038-3045

Název nakladatele

European Language Resources Association

Místo vydání

Torino, Italy

Místo konání akce

Torino, Italy

Datum konání akce

22. 5. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—