RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vasilev, Viacheslav, Agafonova, Julia, Gerasimenko, Nikolai, Kapitanov, Alexander, Mikhailova, Polina, Mironova, Evelina, Dimitrov, Denis
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929710082031616
author Vasilev, Viacheslav
Agafonova, Julia
Gerasimenko, Nikolai
Kapitanov, Alexander
Mikhailova, Polina
Mironova, Evelina
Dimitrov, Denis
author_facet Vasilev, Viacheslav
Agafonova, Julia
Gerasimenko, Nikolai
Kapitanov, Alexander
Mikhailova, Polina
Mironova, Evelina
Dimitrov, Denis
contents Text-to-image generation models have gained popularity among users around the world. However, many of these models exhibit a strong bias toward English-speaking cultures, ignoring or misrepresenting the unique characteristics of other language groups, countries, and nationalities. The lack of cultural awareness can reduce the generation quality and lead to undesirable consequences such as unintentional insult, and the spread of prejudice. In contrast to the field of natural language processing, cultural awareness in computer vision has not been explored as extensively. In this paper, we strive to reduce this gap. We propose a RusCode benchmark for evaluating the quality of text-to-image generation containing elements of the Russian cultural code. To do this, we form a list of 19 categories that best represent the features of Russian visual culture. Our final dataset consists of 1250 text prompts in Russian and their translations into English. The prompts cover a wide range of topics, including complex concepts from art, popular culture, folk traditions, famous people's names, natural objects, scientific achievements, etc. We present the results of a human evaluation of the side-by-side comparison of Russian visual concepts representations using popular generative models.
format Preprint
id arxiv_https___arxiv_org_abs_2502_07455
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation
Vasilev, Viacheslav
Agafonova, Julia
Gerasimenko, Nikolai
Kapitanov, Alexander
Mikhailova, Polina
Mironova, Evelina
Dimitrov, Denis
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Text-to-image generation models have gained popularity among users around the world. However, many of these models exhibit a strong bias toward English-speaking cultures, ignoring or misrepresenting the unique characteristics of other language groups, countries, and nationalities. The lack of cultural awareness can reduce the generation quality and lead to undesirable consequences such as unintentional insult, and the spread of prejudice. In contrast to the field of natural language processing, cultural awareness in computer vision has not been explored as extensively. In this paper, we strive to reduce this gap. We propose a RusCode benchmark for evaluating the quality of text-to-image generation containing elements of the Russian cultural code. To do this, we form a list of 19 categories that best represent the features of Russian visual culture. Our final dataset consists of 1250 text prompts in Russian and their translations into English. The prompts cover a wide range of topics, including complex concepts from art, popular culture, folk traditions, famous people's names, natural objects, scientific achievements, etc. We present the results of a human evaluation of the side-by-side comparison of Russian visual concepts representations using popular generative models.
title RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2502.07455