The BLA Benchmark: Investigating Basic Language Abilities of Multimodal Models

Creators
Publication date 2023
Description BLA is a novel, automatically constructed benchmark to evaluate multimodal models on basic linguistic constructions—active-passive voice, coordination, and relative clauses—that even preschool children can typically master.
Publisher GitHub
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
  • Interfacultary Research - Institute for Logic, Language and Computation (ILLC)
Document type Dataset
Related publication The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models
Other links https://github.com/shin-ee-chen/BLA
Permalink to this page
Back