KoBALT, an expert-crafted 700-question Korean linguistic benchmark, finds that even the best LLM answers only 61% correctly, with human preference ratings correlating moderately with benchmark accuracy.
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
-
KoBALT: Korean Benchmark For Advanced Linguistic Tasks
KoBALT, an expert-crafted 700-question Korean linguistic benchmark, finds that even the best LLM answers only 61% correctly, with human preference ratings correlating moderately with benchmark accuracy.