.png){kind=icon}
.png){kind=icon}
Return
Memory recall-driven multi-view semantic inference for offensive language detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2026.132948.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The detection of offensive language plays a critical role in maintaining the health of online communities, preventing cyberbullying, and fostering inclusive communication. Current approaches utilize facilitated LLMs for direct aggressiveness classification, but flaws in complex contextual reasoning and in the detection of subtle cues in conversational environments greatly reducing detection performance. To address the aforementioned challenges, we proposes the Memory Recall-Driven Multi-View Semantic Inference (MR-MVSI) model. Specifically, we first build a multi-view semantic inference module that enables the model to effectively capture subtle contextual cues and underlying emotional features from situational backgrounds, communicative targets, and emotions. Meanwhile, we employed a self-check mechanism to discriminate and regenerate the generated information, thereby ensuring the rigor and reliability of the inference process. In addition, we introduce a training memory recall module, which embeds the input samples into a highly semantic space and retrieves the most relevant memory segments to de-interpret complex linguistic patterns, thus significantly improving the detection accuracy. The experimental results demonstrate that our proposed MR-MVSI model achieves superior performance across all three benchmark datasets (OLID, HateXplain, and HatEval), with performance improvements of , , and respectively.
Keywords:
offensive language detection
multi-view semantic inference
memory recall
contextual reasoning
LLMs
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W