CCL25-Eval任务10系统报告：基于提示的大型语言模型融合用于细粒度中文仇恨言论检测
System Report for CCL25-Eval Task 10: Prompt-Driven Large Language Model Merge for Fine-Grained Chinese Hate Speech Detection
AI总结：
本文提出基于提示的LLM融合框架，通过三阶段方法提升细粒度中文仇恨言论检测的性能。
摘要：
中文社交媒体上仇恨言论的泛滥对社会造成了紧迫的风险，然而传统系统难以解码依赖上下文的修辞策略和演变俚语。为弥合这一差距，我们提出了一种新的三阶段基于LLM的框架：提示工程、监督微调和LLM融合。首先，设计了具有上下文意识的提示以指导LLM提取隐含的仇恨模式。其次，在监督微调过程中整合任务特定特征以增强领域适应性。最后，融合微调后的LLM提高了对分布外情况的鲁棒性。在STATE-ToxiCN基准测试上的评估验证了该框架的有效性，证明了在检测细粒度仇恨言论方面优于基线方法。
英文摘要：
The proliferation of hate speech on Chinese social media poses urgent societal risks, yet traditional systems struggle to decode context-dependent rhetorical strategies and evolving slang. To bridge this gap, we propose a novel three-stage LLM-based framework: Prompt Engineering, Supervised Fine-tuning, and LLM Merging. First, context-aware prompts are designed to guide LLMs in extracting implicit hate patterns. Next, task-specific features are integrated during supervised fine-tuning to enhance domain adaptation. Finally, merging fine-tuned LLMs improves robustness against out-of-distribution cases. Evaluations on the STATE-ToxiCN benchmark validate the framework's effectiveness, demonstrating superior performance over baseline methods in detecting fine-grained hate speech.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
