IS2Lab/S-Eval

S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models

44
/ 100
Emerging

This project provides a comprehensive set of evaluation prompts to test the safety of Large Language Models (LLMs) against various harmful outputs. It takes LLM responses to these prompts as input and helps identify if the model generates content related to crimes, hate speech, privacy violations, or other unsafe categories. This is primarily for AI safety researchers and developers who are building or deploying LLMs and need to ensure their models are not generating problematic content.

111 stars.

Use this if you need a structured, multi-dimensional benchmark to systematically assess the safety performance of your Large Language Models.

Not ideal if you are a casual user looking for a simple, single-metric safety check for a pre-existing LLM.

AI-safety LLM-evaluation harmful-content-detection model-testing responsible-AI
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

111

Forks

6

Language

License

Last pushed

Feb 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/IS2Lab/S-Eval"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.