S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
-
Updated
Oct 14, 2025
#
safety-evaluation
Here are 5 public repositories matching this topic...
Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)
-
Updated
Mar 1, 2025 - Jupyter Notebook
Octopus is an automated LLM safety evaluator designed to help establish a security governance framework for large models and accelerate their safe and controllable application.
-
Updated
Oct 14, 2025 - Python
Open-source AI safety benchmark testing how models handle tricky gray-zone requests. CLI for running benchmarks + web dashboard for exploring results.
open-source benchmark dashboard openai ai-safety cli-tool ai-research llm-evaluation safety-evaluation harmfulness-detection safe-completion
-
Updated
Aug 20, 2025 - Python
Foundation for building safer generative-AI systems — includes example safety labs for bias detection, toxicity analysis, and RLHF-based response alignment.
machine-learning deep-learning transformers pytorch alignment content-filtering ai-safety bias-detection responsible-ai huggingface llm prompt-engineering rlhf safety-evaluation reward-modeling
-
Updated
Oct 20, 2025 - Python
Improve this page
Add a description, image, and links to the safety-evaluation topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the safety-evaluation topic, visit your repo's landing page and select "manage topics."