allenai / safety-evalLinks
A simple evaluation of generative language models and safety classifiers.
☆64Updated this week
Alternatives and similar repositories for safety-eval
Users that are interested in safety-eval are comparing it to the libraries listed below
Sorting:
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆91Updated 9 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆128Updated 2 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆111Updated 6 months ago
- Improving Alignment and Robustness with Circuit Breakers☆233Updated 11 months ago
- ☆98Updated 10 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆269Updated 3 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…☆138Updated 3 months ago
- [ICLR 2025] General-purpose activation steering library☆102Updated 3 weeks ago
- Run safety benchmarks against AI models and view detailed reports showing how well they performed.☆104Updated this week
- ☆39Updated 2 years ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆105Updated last year
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆186Updated 7 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.