LLMs like o1 outperform humans on most linguistic olympiad puzzle types except writing systems and understudied languages, with insights applied to the new task of puzzle generation.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can LLMs Generate and Solve Linguistic Olympiad Puzzles?
LLMs like o1 outperform humans on most linguistic olympiad puzzle types except writing systems and understudied languages, with insights applied to the new task of puzzle generation.