Introduces mSCoRe, a multilingual skill-annotated commonsense benchmark built from human-annotated seeds and LLM-based complexity scaling, and shows all eight tested LLMs degrade as complexity increases.
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
-
mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning
Introduces mSCoRe, a multilingual skill-annotated commonsense benchmark built from human-annotated seeds and LLM-based complexity scaling, and shows all eight tested LLMs degrade as complexity increases.