grushaaaaa/crosslingual-refusal-en-hi download history

grushaaaaa/crosslingual-refusal-en-hi is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 24 times (10 in the last 7 days), and 86 times in total. It ranks #326,781 among datasets by monthly downloads.

Cross-Lingual Refusal Benchmark (English–Hindi) A parallel English/Hindi red-teaming benchmark for measuring whether an LLM's refusal behaviour is language-dependent — i.e. whether a model that refuses a harmful request in English complies with the same request in Hindi. Every English

Open grushaaaaa/crosslingual-refusal-en-hi on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.