Release PairedSafety public evaluation dataset on Hugging Face

Hi @mengyahuUSTC-PU 🤗

Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability. If you are one of the authors, you can submit it at https://huggingface.co/papers/2604.26052

The paper page lets people discuss about your paper and lets them find artifacts about it (your dataset for instance), you can also claim the paper as yours which will show up on your public profile at HF, and add your GitHub link.

I saw in your GitHub repository that you have shared a highly valuable public supporting evaluation dataset (containing the 600 prompts, raw responses from six models, and the grader severity labels) under analysis/public_mini_eval/data/.

Would you like to host this evaluation dataset on https://huggingface.co/datasets?
Hosting it on Hugging Face will give it more visibility and enable better discoverability within the AI safety community, while also allowing people to easily do:

from datasets import load_dataset

dataset = load_dataset("your-hf-org-or-username/PairedSafety")

If you're down, leaving a guide here: https://huggingface.co/docs/datasets/loading.

Besides that, there's the dataset viewer which allows people to quickly explore the prompts, responses, and labels directly in the browser.

After uploaded, we can also link the dataset to the paper page (read here) so people can discover your work.

Let me know if you're interested/need any guidance!

Kind regards,

Niels

Start with the dataset in analysis/public_mini_eval/data/ and the Hugging Face Datasets loading guide linked in the issue. Upload the PairedSafety evaluation data to Hugging Face, verify that Python's load_dataset example works and the dataset viewer exposes the prompts, responses, and labels, then link it to the paper page if applicable.