C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts
Chenxi Qing, Junxi Wu, Zheng Liu, Yixiang Qiu, Hongyao Yu + 3 more
TLDR
C-ReD is a new Chinese benchmark for detecting AI-generated text, improving diversity and generalization over prior datasets.
Key contributions
- Introduces C-ReD, a comprehensive Chinese benchmark for detecting AI-generated text.
- Derived from real-world prompts, addressing realism and domain coverage gaps.
- Features diverse LLM-generated content, overcoming prior data homogeneity issues.
- Demonstrates strong generalization to unseen LLMs and external Chinese datasets.
Why it matters
C-ReD is a vital Chinese benchmark for detecting AI-generated text. It overcomes prior dataset limitations in model diversity and real-world prompt realism. This is crucial for mitigating LLM risks like academic dishonesty and phishing.
Original Abstract
Recently, large language models (LLMs) are capable of generating highly fluent textual content. While they offer significant convenience to humans, they also introduce various risks, like phishing and academic dishonesty. Numerous research efforts have been dedicated to developing algorithms for detecting AI-generated text and constructing relevant datasets. However, in the domain of Chinese corpora, challenges remain, including limited model diversity and data homogeneity. To address these issues, we propose C-ReD: a comprehensive Chinese Real-prompt AI-generated Detection benchmark. Experiments demonstrate that C-ReD not only enables reliable in-domain detection but also supports strong generalization to unseen LLMs and external Chinese datasets-addressing critical gaps in model diversity, domain coverage, and prompt realism that have limited prior Chinese detection benchmarks. We release our resources at https://github.com/HeraldofLight/C-ReD.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.