Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech

大锤还是手术刀？一种针对隐晦仇恨言论的细粒度自适应框架

Abstract: Unlike explicit attacks with obvious profanity, implicit hate speech hides malice within seemingly compliant expressions through metaphors and contextual hints, making its detection in online content review challenging.

摘要： 与带有明显亵渎词汇的显性攻击不同，隐晦的仇恨言论通过隐喻和语境暗示，将恶意隐藏在看似合规的表达中，这使得在线内容审核中的检测工作极具挑战性。

While existing PLM- or LLM-based methods perform well, they typically apply a single reasoning process to all samples. This overlooks fine-grained linguistic nuances and causes unnecessary computation for simpler cases.

虽然现有的基于预训练语言模型（PLM）或大语言模型（LLM）的方法表现良好，但它们通常对所有样本应用单一的推理过程。这忽略了细粒度的语言细微差别，并导致对简单案例造成不必要的计算浪费。

We observe that online hate speech is not monolithic but manifests in varied forms. We therefore define three fine-grained categories: Shallow, Targeted, and Context-Dependent.

我们观察到，在线仇恨言论并非单一形态，而是以多种形式呈现。因此，我们定义了三个细粒度类别：浅层（Shallow）、针对性（Targeted）和语境依赖型（Context-Dependent）。

Accordingly, we propose Fine-grained Adaptive Implicit Hate speech Detection (FAID), a novel framework that first performs fine-grained classification and then adapts to specific categories.

据此，我们提出了细粒度自适应隐晦仇恨言论检测框架（FAID），这是一种首先进行细粒度分类，然后针对特定类别进行自适应处理的新型框架。

Specifically, for Shallow samples with surface-identifiable intents, the framework adopts lightweight prompt-tuning for rapid classification; for Targeted comments that bind malicious intent to concealed targets, we design knowledge augmentation to iteratively refine the model and reveal hidden targets; for Context-Dependent comments lacking background information, we utilize an agentic framework that automatically generates prompts to evolve context, infer missing background information and identify ambiguous malicious intents.

具体而言，对于意图易于识别的“浅层”样本，该框架采用轻量级提示微调（prompt-tuning）以实现快速分类；对于将恶意意图绑定到隐蔽目标的“针对性”评论，我们设计了知识增强机制，通过迭代优化模型来揭示隐藏目标；对于缺乏背景信息的“语境依赖型”评论，我们利用代理（agentic）框架自动生成提示，以演化语境、推断缺失的背景信息并识别模糊的恶意意图。

This adaptive architecture focuses computational resources on complex implicit samples while avoiding redundant reasoning for shallow samples. Experiments on four benchmark datasets demonstrate that FAID significantly outperforms SOTA baselines.

这种自适应架构将计算资源集中在复杂的隐晦样本上，同时避免了对浅层样本的冗余推理。在四个基准数据集上的实验表明，FAID 的性能显著优于当前的最先进（SOTA）基准模型。