As large language models (LLMs) are increasingly deployed in diverse cultural environments, evaluating their cultural understanding capability has become essential for ensuring trustworthy and culturally aligned applications. However, most existing benchmarks lack comprehensiveness and are challenging to scale and adapt across different cultural contexts, because their frameworks often lack guidance from well-established cultural theories and tend to rely on expert-driven manual annotations. To address these issues, we propose CultureScope, the most comprehensive evaluation framework to date for assessing cultural understanding in LLMs. Inspired by the cultural iceberg theory, we design a novel dimensional schema for cultural knowledge classification, comprising 3 layers and 140 dimensions, which guides the automated construction of culture-specific knowledge bases and corresponding evaluation datasets for any given languages and cultures. Experimental results demonstrate that our method can effectively evaluate cultural understanding. They also reveal that existing large language models lack comprehensive cultural competence, and merely incorporating multilingual data does not necessarily enhance cultural understanding.

A new Chinese video game has created a buzz worldwide after it sold more than 10 million copies within three days, becoming the most successful game of all time to emerge from the country. According to 2023 estimates, China's gaming industry is roughly worth 40bn. Black Myth: Wukong, produced by developer Game Science (GS), has already generated an estimated 800-900m in revenue to date and will help project Chinese culture to a global audience. The game, believed to be China's first AAA video game, was developed at a reported cost of about 70m over six years. AAA is a classification used to denote a high-budget or high-profile game from a large video game developer.

Despite the rapid development of Chinese vision-language models (VLMs), most existing Chinese vision-language (VL) datasets are constructed on Western-centric images from existing English VL datasets. The cultural bias in the images makes these datasets unsuitable for evaluating VLMs in Chinese culture. To remedy this issue, we present a new Chinese Vision- Language Understanding Evaluation (CVLUE) benchmark dataset, where the selection of object categories and images is entirely driven by Chinese native speakers, ensuring that the source images are representative of Chinese culture. The benchmark contains four distinct VL tasks ranging from image-text retrieval to visual question answering, visual grounding and visual dialogue. We present a detailed statistical analysis of CVLUE and provide a baseline performance analysis with several open-source multilingual VLMs on CVLUE and its English counterparts to reveal their performance gap between English and Chinese. Our in-depth category-level analysis reveals a lack of Chinese cultural knowledge in existing VLMs. We also find that fine-tuning on Chinese culture-related VL datasets effectively enhances VLMs' understanding of Chinese culture.

Large vision-language models (VLMs) have demonstrated remarkable abilities in understanding everyday content. However, their performance in the domain of art, particularly culturally rich art forms, remains less explored. As a pearl of human wisdom and creativity, art encapsulates complex cultural narratives and symbolism. In this paper, we offer the Pun Rebus Art Dataset, a multimodal dataset for art understanding deeply rooted in traditional Chinese culture. We focus on three primary tasks: identifying salient visual elements, matching elements with their symbolic meanings, and explanations for the conveyed messages. Our evaluation reveals that state-of-the-art VLMs struggle with these tasks, often providing biased and hallucinated explanations and showing limited improvement through in-context learning. By releasing the Pun Rebus Art Dataset, we aim to facilitate the development of VLMs that can better understand and interpret culturally specific content, promoting greater inclusiveness beyond English-based corpora.

Do mass media influence people's opinion of other countries? Using BERT, a deep neural network-based natural language processing model, we analyze a large corpus of 267,907 China-related articles published by The New York Times since 1970. We then compare our output from The New York Times to a longitudinal data set constructed from 101 cross-sectional surveys of the American public's views on China. We find that the reporting of The New York Times on China in one year explains 54% of the variance in American public opinion on China in the next. Our result confirms hypothesized links between media and public opinion and helps shed light on how mass media can influence public opinion of foreign countries.

I never learned anything in the Saturday-morning Chinese school I was forced to attend as a child, but that's not what motivates my choice here. There were plenty of reasons for my poor performance in those classes--my resentment at having to miss the "Super Friends" cartoon being just one of them--so I don't blame Chinese characters for my failure. No, my objection is a practical one: I'm a fan of literacy, and Chinese characters have been an obstacle to literacy for millennia. With a phonetic writing system like an alphabet or a syllabary, you need only learn a few dozen symbols and you can read most everything printed in a newspaper. With Chinese characters, you have to learn three thousand.