C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts
This benchmark provides a more realistic and diverse evaluation resource for Chinese AI-generated text detection, benefiting researchers working on detection algorithms for Chinese corpora.
The authors introduce C-ReD, a comprehensive Chinese benchmark for AI-generated text detection using real-world prompts, addressing gaps in model diversity, domain coverage, and prompt realism. Experiments show it enables reliable in-domain detection and strong generalization to unseen LLMs and external datasets.
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.