instance-level
AFRLA-assessor-instance-level-results
Assessors For Regression: Loss Analysis - Assessor Instance Level Results
Instance level results for assessors models trained on the AFRLA - Instance Level Results dataset.
At the moment of upload, results for XGBoost and linear regression models are available, with results from the former in 5 different seeds. Results are available for all 11 tasks described in the original dataset as well as for 6 different types of error (losses):
Loss name
Description… See the full description on the dataset page: https://huggingface.co/datasets/DaniFrame/AFRLA-assessor-instance-level-results.AFRLA-instance-level-results
Assessors For Regression: Loss Analysis - Instance Level Results
AFRLA - Instance Level Results is a collection of predictions at the instance/example level for eleven different regression tasks tested on 255 tree-based models (also called "base systems"). The aim of this dataset is to provide example-level results to train assessor models to predict performance of the tree-based models.
The dataset
The dataset presents eleven sections (one per regression task), with… See the full description on the dataset page: https://huggingface.co/datasets/DaniFrame/AFRLA-instance-level-results.instance-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.