Open Unlearning

community

https://arxiv.org/abs/2506.12618

locuslab

AI & ML interests

Large Language Model unlearning

Recent Activity

VineethD new activity 18 days ago

open-unlearning/README:Llama models for GA and/or WGA

pratyushmaini authored a paper 4 months ago

Model-tuning Via Prompts Makes NLP Models Adversarially Robust

pratyushmaini authored a paper 4 months ago

Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic

View all activity

VineethD

in open-unlearning/README 18 days ago

Llama models for GA and/or WGA

#1 opened 19 days ago by

pratyushmaini

authored 5 papers 4 months ago

Model-tuning Via Prompts Makes NLP Models Adversarially Robust

Paper • 2303.07320 • Published Mar 13, 2023

Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic

Paper • 2404.07177 • Published Apr 10, 2024 • 1

Rethinking LLM Memorization through the Lens of Adversarial Compression

Paper • 2404.15146 • Published Apr 23, 2024

OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics

Paper • 2506.12618 • Published Jun 14

BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining

Paper • 2508.10975 • Published Aug 14 • 60

Dornavineeth

updated a Space 5 months ago

README

Dornavineeth

published a Space 5 months ago

README

Dornavineeth

updated a collection 5 months ago

TOFU Models w & w/o Knowledge

Models with and without TOFU author knowledge, used to evaluate metric faithfulness (see: https://arxiv.org/pdf/2506.12618). • 60 items • Updated Jun 30 • 1