datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
blimp_nl
BLiMP-NL: A Corpus of Dutch Minimal Pairs and Acceptability Judgments for Language Model Evaluation
[A] corpus of 8400 Dutch sentence pairs, intended primarily for the grammatical evaluation of language models. Each pair consists of a grammatical sentence and a minimally different ungrammatical sentence. The corpus covers 84 paradigms, classified into 22 syntactic phenomena. Ten sentence pairs of each paradigm were created by hand, while the remaining 90 were generated… See the full description on the dataset page: https://huggingface.co/datasets/jmichaelov/blimp_nl.BLiMP-ruBLiMP-ru: Russian BLiMP
extension of RuBLiMP
Dataset Description
This dataset is an adaptation of RuBLiMP (Benchmark of Linguistic Minimal Pairs), designed to evaluate language models’
grammatical knowledge through minimal-pair judgment tasks. This dataset is specifically designed to target L2 transfer and interference. Each
example consists of two nearly identical Russian sentences, one grammatically correct, the other ungrammatical, and the model’s task is to
identify the correct one.
The… See the full description on the dataset page: https://huggingface.co/datasets/elliepreed/BLiMP-ru.