A new 450-scenario benchmark shows that LLMs lag native Persian speakers by 40 to 48 points on taarof-expected interactions, and that fine-tuning on the benchmark narrows the gap.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
We Politely Insist: Your LLM Must Learn the Persian Art of Taarof
A new 450-scenario benchmark shows that LLMs lag native Persian speakers by 40 to 48 points on taarof-expected interactions, and that fine-tuning on the benchmark narrows the gap.