A new 405-question Hindi analogy benchmark shows three multilingual LLMs scoring higher under English prompts than Hindi prompts, with the proposed grounded chain-of-thought prompt adding only 0.27 points on average.
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
-
Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy Evaluation
A new 405-question Hindi analogy benchmark shows three multilingual LLMs scoring higher under English prompts than Hindi prompts, with the proposed grounded chain-of-thought prompt adding only 0.27 points on average.