princeton-nlp / benign-data-breaks-safety
☆33Updated 5 months ago
Alternatives and similar repositories for benign-data-breaks-safety:
Users that are interested in benign-data-breaks-safety are comparing it to the libraries listed below
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆41Updated 4 months ago
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated 8 months ago
- ☆19Updated 7 months ago
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆22Updated 5 months ago
- ☆20Updated last week
- ☆42Updated last month
- ☆50Updated 8 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆82Updated 8 months ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆69Updated 5 months ago
- The official code of the paper "A Closer Look at Machine Unlearning for Large Language Models".☆24Updated 3 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆49Updated 3 weeks ago
- Official repo for NeurIPS'24 paper "WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models"☆13Updated 3 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆73Updated last month
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆89Updated 10 months ago
- ☆16Updated last week
- ☆25Updated 10 months ago
- Restore safety in fine-tuned language models through task arithmetic☆27Updated 11 months ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆23Updated 8 months ago
- ☆30Updated 10 months ago
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated 4 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆56Updated 5 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆59Updated 2 months ago
- ☆19Updated 5 months ago
- ☆12Updated 3 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆88Updated 6 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆78Updated 10 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆48Updated 5 months ago
- ☆16Updated 2 weeks ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆18Updated last year
- [EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156☆30Updated last year