ResearchBenchmarksToxicity Detection on Chinese Toxicity Detection Split perturbation (test)Follow0.9734Detection RateCA-CoT0.5747680.6782590.781750.885241May 30, 2025Evaluation ResultsMethodMethodLinksDetection RateCA-CoTBackbone=GPT-4o-mini,...Backbone=GPT-4o-mini, Prompting=Chinese-Aware Chain-of-Thought2025.050.9734ICLBackbone=GPT-4o-mini,...Backbone=GPT-4o-mini, Prompting=In-Context Learning2025.050.8713No ICLBackbone=GPT-4o-mini,...Backbone=GPT-4o-mini, Prompting=Zero-shot (No ICL)2025.050.5901