datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
fine_grained_unlearning
Fine-Grained Knowledge Unlearning — Namesake Benchmark
A benchmark for fine-grained knowledge unlearning: can a method remove a fact
about entity X without damaging the same fact on entity Y, when X and Y
have (near-)identical names and share exactly that one attribute?
Each sample is a pair of real people who
share an identical or near-identical name,
share one career element (e.g. both are basketball players) — the fact to
unlearn on X and retain on Y,
differ on everything… See the full description on the dataset page: https://huggingface.co/datasets/ernlavr/fine_grained_unlearning.Unlearning_Yelp_Polarityinstance-level-tofu-unlearning
Instance-Level TOFU Benchmark
This dataset provides an instance-level adaptation of the TOFU (Maini et al, 2024) dataset for evaluating in-context unlearning in large language models (LLMs). Unlike the original TOFU benchmark, which focuses on entity-level unlearning, this version targets selective memory erasure at the instance level — i.e., forgetting specific facts about an entity.
It is compatible for evaluation with the locuslab/tofu_ft_llama2-7b model, which was fine-tuned on… See the full description on the dataset page: https://huggingface.co/datasets/chowfi/instance-level-tofu-unlearning.Unlearning_SST2StereoSet-UK-Unlearning
StereoSet-UK Unlearning
StereoSet-UK Unlearning contains 2,101 Ukrainian full-sentence triplets derived from the
intrasentence portion of the StereoSet development set. The Ukrainian sentences were translated
with the DeepL API and received technical cleanup. English source text is omitted.
Each triplet assigns the stereotype sentence to forget_uk, the anti-stereotype sentence to
retain_uk, and the unrelated sentence to control_uk. Five items with duplicate translated
candidates… See the full description on the dataset page: https://huggingface.co/datasets/FairForget/StereoSet-UK-Unlearning.unlearning_negative