# ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark

arXiv: https://arxiv.org/abs/2506.10960 · HTML: https://mlsanity.com/paper/2506.10960/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- First posted on arXiv 12 Jun 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Built on by (most cited first, 7 of 7)

- [GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules](https://mlsanity.com/paper/2603.01724/) (2026)
- [Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety](https://mlsanity.com/paper/2606.27632/) (2026)
- [Calling the Bluff: Detecting Ever-Shifting Harmful Chat Dialogue via Ordered Reasoning Chain Regularization](https://mlsanity.com/paper/2608.08451/) (2026)
- [VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation](https://mlsanity.com/paper/2608.15600/) (2026)
- [EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion](https://mlsanity.com/paper/2608.27844/) (2026)
- [Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges](https://mlsanity.com/paper/2609.01210/) (2026)
- [SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation](https://mlsanity.com/paper/2609.05843/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have been increasingly applied to automated harmful content detection tasks, assisting moderators in identifying policy violations and improving the overall efficiency and accuracy of content review. However, existing resources for harmful content detection are predominantly focused on English, with Chinese datasets remaining scarce and often limited in scope. We present a comprehensive, professionally annotated benchmark for Chinese content harm detection, which covers six representative categories and is constructed entirely from real-world data. Our annotation process further yields a knowledge rule base that provides explicit expert knowledge to assist LLMs in Chinese harmful content detection. In addition, we propose a knowledge-augmented baseline that integrates both human-annotated knowledge rules and implicit knowledge from large language models, enabling smaller models to achieve performance comparable to state-of-the-art LLMs. Code and data are available at https://github.com/zjunlp/ChineseHarm-bench.