oliverdk/user-gender-adversarial-Qwen2.5-14B-Instruct download history

oliverdk/user-gender-adversarial-Qwen2.5-14B-Instruct is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 8 times (2 in the last 7 days), and 154 times in total. It ranks #637,263 among datasets by monthly downloads.

Dataset Card for Dataset Name Adversarial gender prompts with refusal responses. Model refuses to reveal user's gender. Generated by Qwen2.5-14B-Instruct. Filtered with GPT-4.1 to remove gender leakage. Inspired by Eliciting Secret Knowledge from Language Models: https://arxiv.org/abs/2

Open oliverdk/user-gender-adversarial-Qwen2.5-14B-Instruct on Hugging Face

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