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
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆89Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆193Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆166Updated 8 months ago
- [NeurIPS 2024] How do Large Language Models Handle Multilingualism?☆45Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆149Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆242Updated last year
- LLM Unlearning☆177Updated 2 years ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆94Updated 11 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆99Updated 6 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆86Updated 7 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆121Updated last year
- [ICLR 2025] General-purpose activation steering library☆119Updated 2 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆99Updated 2 years ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆107Updated last year
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆166Updated 2 years ago
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated last year
- ☆51Updated 2 years ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆89Updated 6 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
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆99Updated last year
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆80Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆170Updated last year
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆155Updated 5 months ago
- ☆188Updated last year
- FeatureAlignment = Alignment + Mechanistic Interpretability☆31Updated 8 months ago
- ☆103Updated last year
- Multilingual safety benchmark for Large Language Models☆54Updated last year
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆32Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 10 months ago