ResearchBenchmarksToxicity Detection on Chinese Toxicity Detection Overall (test)Follow2.71Error RateNo ICL2.65883.00443.353.6956May 30, 2025Evaluation ResultsMethodMethodLinksError RateNo ICLBackbone=GPT-4o-mini,...Backbone=GPT-4o-mini, Prompting=Zero-shot (No ICL)2025.052.71CA-CoTBackbone=GPT-4o-mini,...Backbone=GPT-4o-mini, Prompting=Chinese-Aware Chain-of-Thought2025.053.15ICLBackbone=GPT-4o-mini,...Backbone=GPT-4o-mini, Prompting=In-Context Learning2025.053.99