kevinyaobytedance / llm_unlearn
LLM Unlearning
☆112Updated 10 months ago
Related projects: ⓘ
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆79Updated 3 months ago
- Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆55Updated 2 months ago
- A resource repository for machine unlearning in large language models☆131Updated this week
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆64Updated 2 weeks ago
- ☆27Updated 3 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆34Updated 4 months ago
- ☆27Updated 3 months ago
- ☆32Updated 11 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆61Updated 4 months ago
- Official code implementation of SKU, Accepted by ACL 2024 Findings☆11Updated 4 months ago
- ☆37Updated 10 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆99Updated 10 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆81Updated this week
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models☆50Updated 2 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆57Updated 6 months ago
- ☆63Updated 10 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆46Updated last month
- ☆143Updated 9 months ago
- ☆21Updated 2 months ago
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆59Updated last year
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆109Updated last week
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆96Updated last week
- Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models☆22Updated 11 months ago
- [ACL2024-Main] Data and Code for WaterBench: Towards Holistic Evaluation of LLM Watermarks☆17Updated 10 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆77Updated 4 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆48Updated 5 months ago
- [EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156☆21Updated 9 months ago
- Awesome LLM Jailbreak academic papers☆61Updated 10 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆110Updated 4 months ago
- Code for the ACL-2022 paper "Knowledge Neurons in Pretrained Transformers"☆148Updated 4 months ago