CulturalBench

Domain:

natural language processing

Record type:

dataset

Creator:

kel

Host:

CulturalBench is a set of 1,227 human-written and human-verified questions for effectively assessing LLMs’ cultural knowledge, covering 45 global regions including the underrepresented ones like Bangladesh, Zimbabwe, and Peru.

Visit

huggingface.co

Licenses

cc-by-4.0

CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming

Robust, diverse, and challenging cultural knowledge benchmarks are essential for measuring our progr

CulturalBench: A Robust, Diverse and Challenging Benchmark for Measuring LMs' Cultural Knowledge Through Human-AI Red-Teaming