locuslab / open-unlearningLinks
The one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE, WMDP, and many unlearning methods. All features: benchmarks, methods, evaluations, models etc. are easily extensible.
☆368Updated last month
Alternatives and similar repositories for open-unlearning
Users that are interested in open-unlearning are comparing it to the libraries listed below
Sorting:
- A resource repository for machine unlearning in large language models☆484Updated last month
- Python package for measuring memorization in LLMs.☆166Updated 2 months ago
- A survey on harmful fine-tuning attack for large language model☆206Updated this week
- LLM Unlearning☆174Updated last year
- ☆166Updated last month
- A resource repository for representation engineering in large language models☆135Updated 10 months ago
- A toolkit to assess data privacy in LLMs (under development)☆62Updated 8 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆150Updated 4 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆84Updated 5 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆111Updated 6 months ago
- ☆60Updated last year
- ☆27Updated 6 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆164Updated last year
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆89Updated last year
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆25Updated 6 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆46Updated 10 months ago
- [ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models☆36Updated 9 months ago
- Improving Alignment and Robustness with Circuit Breakers☆233Updated 11 months ago
- ☆28Updated last year
- "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning" by Chongyu Fan*, Jiancheng Liu*, Licong Lin*, Jingh…☆32Updated 2 months ago
- ☆39Updated 10 months ago
- UP-TO-DATE LLM Watermark paper. 🔥🔥🔥☆354Updated 9 months ago
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆321Updated last year
- Official github page for the paper "Evaluating Deep Unlearning in Large Language Model"☆14Updated 4 months ago
- ☆24Updated last year
- Code for watermarking language models☆82Updated last year
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆57Updated last week
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆138Updated 3 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆86Updated last year
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆60Updated 11 months ago