Via Ars Technica:
New research released earlier this month titled “We Politely Insist: Your LLM Must Learn the Persian Art of Taarof” shows that mainstream AI language models from OpenAI, Anthropic, and Meta fail to absorb these Persian social rituals, correctly navigating taarof situations only 34 to 42 percent of the time. Native Persian speakers, by contrast, get it right 82 percent of the time. This performance gap persists across large language models such as GPT-4o, Claude 3.5 Haiku, Llama 3, DeepSeek V3, and Dorna, a Persian-tuned variant of Llama 3. …
“Cultural missteps in high-consequence settings can derail negotiations, damage relationships, and reinforce stereotypes,” the researchers write. For AI systems increasingly used in global contexts, that cultural blindness could represent a limitation that few in the West realize exists.
For us provincial types, other cultures have radically different ways of getting business done, and if you don’t know that, or arrogantly don’t care, failure will be your lot on the venture.
This emphasizes where AI may be a weak addition to the quiver of arrows.
Here’s Wikipedia’s page on taarof.
