|国家预印本平台
首页|A Culturally-Rich Romanian NLP Dataset from "Who Wants to Be a Millionaire?" Videos

A Culturally-Rich Romanian NLP Dataset from "Who Wants to Be a Millionaire?" Videos

A Culturally-Rich Romanian NLP Dataset from "Who Wants to Be a Millionaire?" Videos

来源:Arxiv_logoArxiv
英文摘要

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 at Hugging Face.

Alexandru-Gabriel Ganea、Antonia-Adelina Popovici、Adrian-Marius Dumitran

印欧语系科学、科学研究教育

Alexandru-Gabriel Ganea,Antonia-Adelina Popovici,Adrian-Marius Dumitran.A Culturally-Rich Romanian NLP Dataset from "Who Wants to Be a Millionaire?" Videos[EB/OL].(2025-06-06)[2025-06-22].https://arxiv.org/abs/2506.05991.点此复制

评论