bertiev / SimpleSafetyTestsLinks
☆17Updated last year
Alternatives and similar repositories for SimpleSafetyTests
Users that are interested in SimpleSafetyTests are comparing it to the libraries listed below
Sorting:
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆116Updated 8 months ago
- Improving Alignment and Robustness with Circuit Breakers☆238Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆191Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆87Updated last year
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆92Updated 11 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆87Updated 6 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆146Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆105Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆98Updated 5 months ago
- ☆58Updated 2 years ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆98Updated 2 years ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆163Updated 7 months ago
- [ICLR 2025] General-purpose activation steering library☆114Updated last month
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆99Updated last year
- ☆187Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆169Updated last year
- LLM Unlearning☆177Updated 2 years ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆66Updated 11 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆85Updated 7 months ago
- ☆49Updated 2 years ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆292Updated 4 months ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆61Updated 2 years ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆121Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆90Updated last year
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆83Updated last year
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆69Updated 5 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…☆151Updated 5 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆30Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 9 months ago
- Multilingual safety benchmark for Large Language Models☆53Updated last year