AI models get more election questions wrong when asked in Spanish, study shows | TechCrunch
Briefly

from TechCrunch3 months ago
The AI Democracy Projects study shows that AI models provided a significantly lower accuracy rate for Spanish-language election questions, revealing systemic bias in AI.
TechCrunchhttps://techcrunch.com/2024/10/30/ai-models-get-more-election-questions-wrong-when-asked-in-spanish-study-shows/
Across five leading generative AI models, 52% of responses to Spanish-language election queries contained incorrect information, highlighting disparities in AI performance by language.
TechCrunchhttps://techcrunch.com/2024/10/30/ai-models-get-more-election-questions-wrong-when-asked-in-spanish-study-shows/
Read at TechCrunch
#ai-bias #election-questions #spanish-language #generative-ai #tech-study
[
|
]