Skip to content

Benchmark

Bridging the Gap Winogrande cultural inappropriateness annotation cross-language Cohen’s kappa, Sepedi (nso) vs Igbo (ig)

Multilingual benchmarks compare model performance across languages.

Models and systems measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

0.01
Mean
0.01
Median
0
Std dev
0.01
10th percentile
0.01
90th percentile
0.01
Min

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Inter-rater Agreement on Cultural Inappropriateness across Different Target Languagesfigure: A.14, row: nso, column: ig· Bridging the Gap (arXiv:2412.12417v1) data0.01

Data credits: Tuka Alhanai, Adam Kasumovic, Mohammad Ghassemi, Aven Zitzelberger, Jessica Lundin and Guillaume Chabot-Couture. Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments, arXiv:2412.12417v1. CC BY 4.0 article numeric/protocol extract, restructured with values unchanged. No task or model rights asserted. (licence)