zjunlp/ChineseHarm-bench

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark

30
/ 100
Emerging

This project provides a benchmark and models for detecting harmful content in Chinese text across six categories like gambling, pornography, and fraud. It takes Chinese text as input and outputs classifications indicating whether the content is harmful and, if so, its specific category. Content moderators, trust & safety teams, or platform administrators dealing with user-generated content in Chinese would find this tool valuable.

No commits in the last 6 months.

Use this if you need to automatically identify and categorize harmful or policy-violating content within large volumes of Chinese text.

Not ideal if your primary need is for content moderation in languages other than Chinese, or if you require real-time human-in-the-loop content review workflows.

content-moderation online-safety platform-governance chinese-language-processing harmful-content-detection
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 5 / 25

How are scores calculated?

Stars

49

Forks

2

Language

Python

License

MIT

Last pushed

Sep 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zjunlp/ChineseHarm-bench"

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