dsbowen / strong_reject
☆13Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for strong_reject
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆125Updated last month
- Improving Alignment and Robustness with Circuit Breakers☆154Updated 2 months ago
- Steering Llama 2 with Contrastive Activation Addition☆100Updated 6 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆236Updated last month
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆64Updated 9 months ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆200Updated 3 weeks ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆98Updated 7 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆83Updated 6 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆119Updated last month
- Weak-to-Strong Jailbreaking on Large Language Models☆67Updated 9 months ago
- The official evaluation suite and dynamic data release for MixEval.☆224Updated 2 weeks ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆221Updated 2 months ago
- ☆153Updated 11 months ago
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆176Updated last month
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆78Updated last year
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆343Updated 3 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆50Updated last week
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆99Updated 4 months ago
- CRUXEval: Code Reasoning, Understanding, and Execution Evaluation☆115Updated last month
- 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…☆240Updated 9 months ago
- Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆64Updated last week
- ☆16Updated 8 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆107Updated 2 weeks ago
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆65Updated 10 months ago
- A collection of automated evaluators for assessing jailbreak attempts.☆75Updated 4 months ago
- This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Aji…☆209Updated last year
- A simple unified framework for evaluating LLMs☆146Updated 2 weeks ago
- ☆82Updated 4 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆127Updated last month
- Papers about red teaming LLMs and Multimodal models.☆78Updated this week