PulseAugur
EN
LIVE 20:56:33

New framework improves implicit hate speech detection generalization

By PulseAugur Editorial · [2 sources] ·

Researchers have developed ImpSH, a new framework designed to improve the generalizability of implicit hate speech detection models. This triplet-based approach aligns posts with their implied statements and uses context-bounded semi-hard negatives to better distinguish between similar but distinct instances of hate speech. Evaluations on several datasets using BERT and HateBERT models showed that ImpSH can enhance cross-domain performance compared to standard supervised contrastive methods. AI

IMPACT This research could lead to more robust and transferable models for detecting subtle forms of harmful online content.

RANK_REASON The cluster contains an academic paper detailing a new method for a specific NLP task.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New framework improves implicit hate speech detection generalization

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Wicaksono Leksono Muhamad, Yunita Sari ·

    Aligning Implied Statements for Implicit Hate Speech Generalizability with Context-Bounded Semi-hard Negative Mining

    arXiv:2606.18852v1 Announce Type: cross Abstract: Classifying implicit hate speech remains a challenge, as intent is often masked through insinuation and context rather than explicit slurs. Prior supervised contrastive approaches improve in-domain detection but can overfit surfac…

  2. arXiv cs.AI TIER_1 English(EN) · Yunita Sari ·

    Aligning Implied Statements for Implicit Hate Speech Generalizability with Context-Bounded Semi-hard Negative Mining

    Classifying implicit hate speech remains a challenge, as intent is often masked through insinuation and context rather than explicit slurs. Prior supervised contrastive approaches improve in-domain detection but can overfit surface cues and struggle to transfer across datasets. W…

RELATED ENTITIES

RELATED TOPICS