Multilingual Portal: Japan LIFE & BOSAI がいこくごの 生活と防災の情報 | NHK WORLD-JAPAN
ChatGPT Has ‘Goblin’ Mania in the US. In China It Will ‘Catch You Steadily’
OpenAI’s chatbot has some weird linguistic tics in Chinese that are driving users crazy.
Discovering and transmitting abstract knowledge over generations
The complexity of human culture depends on people's ability to discover and transmit abstract knowledge. Studying this ability is crucial to understanding humans' distinctive place among species, but current experimental paradigms focus on the cultural transmission of specific, concrete facts rather than generalizable abstract knowledge. In this paper, we develop a crafting game paradigm to study how people discover abstract knowledge and transmit it via language. We compared individuals playing this game for 40 rounds to chains of four participants playing for 10 rounds each and passing messages to each other sequentially. The individuals performed significantly better over rounds, but the chains did not. Through simulations with language model agents and a follow-up experiment, we find substantial variation in the helpfulness of participants' messages, which may explain the lack of consistent improvement in chains. The ability to learn selectively from the good messages may be essential for improvement over generations.
Download app | NHK WORLD-JAPAN
Enjoy NHK WORLD-JAPAN’s news and programs live and on demand with its free apps for smartphones, tablets and set top boxes.
A Cult AI Computer’s Boom and Bust
Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs
LLMs have been showing limitations when it comes to cultural coverage and competence, and in some cases show regional biases such as amplifying Western and Anglocentric viewpoints. While there have been works analysing the cultural capabilities of LLMs, there has not been specific work on highlighting LLM regional preferences when it comes to cultural-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ). The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan. Moveover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs and show less inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training.
Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs
LLMs have been showing limitations when it comes to cultural coverage and competence, and in some cases show regional biases such as amplifying Western and Anglocentric viewpoints. While there have been works analysing the cultural capabilities of LLMs, there has not been specific work on highlighting LLM regional preferences when it comes to cultural-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ). The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan. Moveover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs and show less inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training.
What can intralingual translation do?
Published in Asia Pacific Translation and Intercultural Studies (Vol. 6, No. 1, 2019)
Cultural Computing with Context-Aware Application: ZENetic Computer
We offer Cultural Computing as a method for cultural translation that uses scientific methods to represent the essential aspects of culture. Including images that heretofore have not been the focus of computing, such as images of Eastern thought and Buddhism, and the Sansui paintings, poetry and kimono that evoke these images, we projected the style of communication developed by Zen schools over hundreds of years into a world for the user to explore – an exotic Eastern Sansui world. Through encounters with Zen Koans and haiku poetry, the user is constantly and sharply forced to confirm the whereabouts of his or her self-consciousness. However, there is no "right answer" to be found anywhere.
PUNCH — languages of tangled.org
the languages people are building in on tangled — every repo, every knot.
Learn Chinese in 5 Hours (for Beginners) - HSK Level 1 | Learn Chinese for Beginners | Conversations
Learn Chinese in 5 Hours (for Beginners) - HSK Level 1 | Learn Chinese for Beginners | Conversations
Kimi K3 - Kimi API Platform
Kimi K3 is our flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence. The Kimi API Platform provides K3, K2.7 Code, K2.6 and other large language model APIs, supporting long context, multimodal understanding, and Tool Calling.
Learning to solve complex tasks by growing knowledge culturally across generations
Knowledge built culturally across generations allows humans to learn far more than an individual could glean from their own experience in a lifetime. Cultural knowledge in turn rests on language: language is the richest record of what previous generations believed, valued, and practiced, and how these evolved over time. The power and mechanisms of language as a means of cultural learning, however, are not well understood, and as a result, current AI systems do not leverage language as a means for cultural knowledge transmission. Here, we take a first step towards reverse-engineering cultural learning through language. We developed a suite of complex tasks in the form of minimalist-style video games, which we deployed in an iterated learning paradigm. Human participants were limited to only two attempts (two lives) to beat each game and were allowed to write a message to a future participant who read the message before playing. Knowledge accumulated gradually across generations, allowing later generations to advance further in the games and perform more efficient actions. Multigenerational learning followed a strikingly similar trajectory to individuals learning alone with an unlimited number of lives. Successive generations of learners were able to succeed by expressing distinct types of knowledge in natural language: the dynamics of the environment, valuable goals, dangerous risks, and strategies for success. The video game paradigm we pioneer here is thus a rich test bed for developing AI systems capable of acquiring and transmitting cultural knowledge.
DeepL Translator | World's Most Accurate Translator
Translate texts & full document files instantly. Accurate translations for individuals and Teams. Millions translate with DeepL every day.
