一作ACL 2026Findings· Findings of ACL
U r BL i MP : A Benchmark for Evaluating the Linguistic Competence of Large Language Models in U rdu
Farah Adeeba · Brian Dillon · Hassan Sajjad · Rajesh Bhatt
摘要
Evaluating how large language models (LLMs) capture the grammatical structure of low-resource languages remains underexplored. This paper presents the Urdu Benchmark of Linguistic Minimal Pairs (UrBLiMP)—a diagnostic suite of 5,696 minimal pairs that contrast grammatical acceptability across ten...