AI models are having trouble giving correct answers to Spanish questions about elections
That’s what a new study from the AI Democracy Projects says. The project is a partnership between Proof News, the fact-checking service Factchequeado, and the San Francisco-based Institute for Advanced Study.
The study discovered a big difference in how true the English and Spanish answers were that were made by five of the best generative AI models: Anthropic’s Claude 3 Opus, Google’s Gemini 1.5 Pro, OpenAI’s GPT-4, Meta’s Llama 3, and Mistral’s Mixtral 8x7B v0.1.
What does it mean if I’m a federal-only voter? And “What is the Electoral College?” were some of the questions the models were asked that were meant to be like the questions an Arizona voter in the upcoming U.S. presidential election might ask. The models were given the same 25 questions in both English and Spanish. Of the answers they gave, 52% of the answers in Spanish were wrong, while only 43% in English were wrong.
The study shows some surprising ways that AI models can be biased and the bad things that bias can do.
According to a research report from HTX Ventures, the trend of crypto companies departing the United States could be halted,…
Metaplanet Inc., a Japanese investment firm, has been admitted to the CoinShares Blockchain Global Equity Index (BLOCK Index). Prominent publicly…
The central bank's CBDC pilot, which is rapidly expanding, has attracted the participation of numerous prominent South Korean banks and…
After first going to a Mt.Gox cold wallet, most of that stash—nearly 30,400 bitcoin BTC—was sent to "1FG2C…Rveoy," and 2,000…
Major banking firms launched the Global Dollar Network, a regulated platform designed to accelerate stablecoin adoption worldwide. Crypto and traditional…
Rune Christensen, co-founder of Sky (formerly MakerDAO), proposes a strictly deflationary model to stop token emissions, in line with MakerDAO’s…