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.
@article{arxiv.2512.09563,
title = {System Report for CCL25-Eval Task 10: Prompt-Driven Large Language Model Merge for Fine-Grained Chinese Hate Speech Detection},
author = {Binglin Wu and Jiaxiu Zou and Xianneng Li},
journal= {arXiv preprint arXiv:2512.09563},
year = {2025}
}