@inproceedings{ganea-etal-2025-culturally,
title = "A Culturally-Rich {R}omanian {NLP} Dataset from ``Who Wants to Be a Millionaire?'' Videos",
author = "Ganea, Alexandru and
Popovici, Antonia-Adelina and
Dumitran, Marius",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.46/",
pages = "378--387",
abstract = "Large Language Models (LLMs) demonstrate varying performance across languages and cultural contexts. This study introduces a novel, culturally-rich, multilingual dataset derived from video recordings of the Romanian game show ``Who Wants to Be a Millionaire?'' (Vrei s{\u{a}} fii Milionar?). We employed an innovative process combining optical character recognition (OCR), automated text extraction, and manual verification to collect question-answer pairs, enriching them with metadata including question domain (e.g., biology, history), cultural relevance (Romanian-specific vs. international), and difficulty. Benchmarking state-of-the-art LLMs, including Romanian-adapted models, on this dataset revealed significant performance disparities: models consistently achieve higher accuracy (80-95{\%}) on international questions compared to Romanian-specific cultural questions (50-75{\%}). We further investigate these differences through experiments involving machine translation of Romanian questions into English and cross-lingual tests using a comparable dataset in French. Our findings underscore the impact of cultural context and data source on LLM performance and offer practical insights for building robust, culturally-aware multilingual NLP systems, especially in educational domains. The dataset is publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ganea-etal-2025-culturally">
<titleInfo>
<title>A Culturally-Rich Romanian NLP Dataset from “Who Wants to Be a Millionaire?” Videos</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandru</namePart>
<namePart type="family">Ganea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonia-Adelina</namePart>
<namePart type="family">Popovici</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marius</namePart>
<namePart type="family">Dumitran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) demonstrate varying performance across languages and cultural contexts. This study introduces a novel, culturally-rich, multilingual dataset derived from video recordings of the Romanian game show “Who Wants to Be a Millionaire?” (Vrei să fii Milionar?). We employed an innovative process combining optical character recognition (OCR), automated text extraction, and manual verification to collect question-answer pairs, enriching them with metadata including question domain (e.g., biology, history), cultural relevance (Romanian-specific vs. international), and difficulty. Benchmarking state-of-the-art LLMs, including Romanian-adapted models, on this dataset revealed significant performance disparities: models consistently achieve higher accuracy (80-95%) on international questions compared to Romanian-specific cultural questions (50-75%). We further investigate these differences through experiments involving machine translation of Romanian questions into English and cross-lingual tests using a comparable dataset in French. Our findings underscore the impact of cultural context and data source on LLM performance and offer practical insights for building robust, culturally-aware multilingual NLP systems, especially in educational domains. The dataset is publicly available.</abstract>
<identifier type="citekey">ganea-etal-2025-culturally</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.46/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>378</start>
<end>387</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Culturally-Rich Romanian NLP Dataset from “Who Wants to Be a Millionaire?” Videos
%A Ganea, Alexandru
%A Popovici, Antonia-Adelina
%A Dumitran, Marius
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F ganea-etal-2025-culturally
%X Large Language Models (LLMs) demonstrate varying performance across languages and cultural contexts. This study introduces a novel, culturally-rich, multilingual dataset derived from video recordings of the Romanian game show “Who Wants to Be a Millionaire?” (Vrei să fii Milionar?). We employed an innovative process combining optical character recognition (OCR), automated text extraction, and manual verification to collect question-answer pairs, enriching them with metadata including question domain (e.g., biology, history), cultural relevance (Romanian-specific vs. international), and difficulty. Benchmarking state-of-the-art LLMs, including Romanian-adapted models, on this dataset revealed significant performance disparities: models consistently achieve higher accuracy (80-95%) on international questions compared to Romanian-specific cultural questions (50-75%). We further investigate these differences through experiments involving machine translation of Romanian questions into English and cross-lingual tests using a comparable dataset in French. Our findings underscore the impact of cultural context and data source on LLM performance and offer practical insights for building robust, culturally-aware multilingual NLP systems, especially in educational domains. The dataset is publicly available.
%U https://aclanthology.org/2025.ranlp-1.46/
%P 378-387
Markdown (Informal)
[A Culturally-Rich Romanian NLP Dataset from “Who Wants to Be a Millionaire?” Videos](https://aclanthology.org/2025.ranlp-1.46/) (Ganea et al., RANLP 2025)
ACL