datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
RWKU
Dataset Card for Real-World Knowledge Unlearning Benchmark (RWKU)
Dataset Summary
RWKU is a real-world knowledge unlearning benchmark specifically designed for large language models (LLMs).
This benchmark contains 200 real-world unlearning targets and 13,131 multi-level forget probes, including 3,268 fill-in-the-blank probes, 2,879 question-answer probes, and 6,984 adversarial-attack probes.
RWKU is designed based on the following three key factors:
For the task setting… See the full description on the dataset page: https://huggingface.co/datasets/jinzhuoran/RWKU.realworld-qa
Real World Records — Evaluation Dataset (QA pairs) + Coverage Summary
TL;DR
A publication-ready evaluation dataset for a Real World Studios ML system, delivered as JSONL (one JSON object per line with input, target, source). It covers Real World Records label/studio/WOMAD history, Peter Gabriel's full discography, and a broad cross-section of the label's artist catalogue with verified catalogue numbers, dates, producers, and collaborations.
Every answer is grounded in a named… See the full description on the dataset page: https://huggingface.co/datasets/rw-robai/realworld-qa.