Hate Speech Detection

Hate speech detection is the task of detecting if communication such as text, audio, and so on contains hatred and or encourages violence towards a person or a group of people. This is usually based on prejudice against 'protected characteristics' such as their ethnicity, gender, sexual orientation, religion, age et al. Some example benchmarks are ETHOS and HateXplain. Models can be evaluated with metrics like the F-score or F-measure.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 76–100 of 507 papers

Title	Date	Tasks	Status
Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content	Feb 11, 2025	Hate Speech DetectionVideo Classification	CodeCode Available
The Impact of Persona-based Political Perspectives on Hateful Content Detection	Feb 1, 2025	DiversityFairness	—Unverified
Cross-Modal Transfer from Memes to Videos: Addressing Data Scarcity in Hateful Video Detection	Jan 26, 2025	Hate Speech DetectionTransfer Learning	CodeCode Available
Evaluating Simple Debiasing Techniques in RoBERTa-based Hate Speech Detection Models	Jan 26, 2025	Hate Speech Detection	—Unverified
Digital Guardians: Can GPT-4, Perspective API, and Moderation API reliably detect hate speech in reader comments of German online newspapers?	Jan 2, 2025	Hate Speech Detection	—Unverified
SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes	Dec 29, 2024	Hate Speech Detection	CodeCode Available
IITR-CIOL@NLU of Devanagari Script Languages 2025: Multilingual Hate Speech Detection and Target Identification in Devanagari-Scripted Languages	Dec 23, 2024	Binary ClassificationDiversity	—Unverified
LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs	Dec 22, 2024	Hate Speech Detectionparameter-efficient fine-tuning	CodeCode Available
SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs	Dec 21, 2024	Hate Speech Detection	—Unverified
Towards Efficient and Explainable Hate Speech Detection via Model Distillation	Dec 18, 2024	Abusive LanguageHate Speech Detection	CodeCode Available
Common Ground, Diverse Roots: The Difficulty of Classifying Common Examples in Spanish Varieties	Dec 16, 2024	FairnessHate Speech Detection	—Unverified
Navigating Dialectal Bias and Ethical Complexities in Levantine Arabic Hate Speech Detection	Dec 14, 2024	Hate Speech Detection	—Unverified
NLPineers@ NLU of Devanagari Script Languages 2025: Hate Speech Detection using Ensembling of BERT-based models	Dec 11, 2024	Data AugmentationHate Speech Detection	CodeCode Available
A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities	Dec 6, 2024	Federated LearningFew-Shot Learning	—Unverified
Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model	Dec 3, 2024	Adversarial AttackHate Speech Detection	CodeCode Available
A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages	Nov 28, 2024	Hate Speech DetectionSurvey	—Unverified
On Importance of Code-Mixed Embeddings for Hate Speech Identification	Nov 27, 2024	Hate Speech DetectionSentence	—Unverified
On Limitations of LLM as Annotator for Low Resource Languages	Nov 26, 2024	Hate Speech DetectionNews Classification	—Unverified
BERT or FastText? A Comparative Analysis of Contextual as well as Non-Contextual Embeddings	Nov 26, 2024	Hate Speech DetectionNews Classification	CodeCode Available
BanglaEmbed: Efficient Sentence Embedding Models for a Low-Resource Language Using Cross-Lingual Distillation Techniques	Nov 22, 2024	Hate Speech DetectionKnowledge Distillation	—Unverified
The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection	Nov 17, 2024	Bias DetectionHate Speech Detection	CodeCode Available
Gender Bias Mitigation for Bangla Classification Tasks	Nov 16, 2024	ClassificationHate Speech Detection	CodeCode Available
A Unified Multi-Task Learning Architecture for Hate Detection Leveraging User-Based Information	Nov 11, 2024	Abusive LanguageHate Speech Detection	—Unverified
Untangling Hate Speech Definitions: A Semantic Componential Analysis Across Cultures and Domains	Nov 11, 2024	Hate Speech Detection	—Unverified
Incorporating Human Explanations for Robust Hate Speech Detection	Nov 9, 2024	Hate Speech Detection	—Unverified

Show:10 25 50

← PrevPage 4 of 21Next →

All datasets Ethos Binary HateXplain Ethos MultiLabel Waseem et al., 2018 AbusEval Automatic Misogynistic Identification HateMM HatEval OffensEval 2019 ToLD-Br bajer_danish_misogyny DKhate

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	BiLSTM + static BE	F1-score	0.8	—	Unverified
2	BERT	F1-score	0.79	—	Unverified
3	BiLSTM+Attention+FT	F1-score	0.77	—	Unverified
4	OPT-175B (few-shot)	F1-score	0.76	—	Unverified
5	CNN+Attention+FT+GV	F1-score	0.74	—	Unverified
6	OPT-175B (one-shot)	F1-score	0.71	—	Unverified
7	OPT-175B (zero-shot)	F1-score	0.67	—	Unverified
8	SVM	F1-score	0.66	—	Unverified
9	Random Forests	F1-score	0.64	—	Unverified
10	Davinci (zero-shot)	F1-score	0.63	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BERT-MRP	AUROC	0.86	—	Unverified
2	BERT-RP	AUROC	0.85	—	Unverified
3	BERT-HateXplain [LIME]	AUROC	0.85	—	Unverified
4	BERT-HateXplain [Attn]	AUROC	0.85	—	Unverified
5	BERT [Attn]	AUROC	0.84	—	Unverified
6	BiRNN-HateXplain [Attn]	AUROC	0.81	—	Unverified
7	BiRNN-Attn [Attn]	AUROC	0.8	—	Unverified
8	CNN-GRU [LIME]	AUROC	0.79	—	Unverified
9	BiRNN [LIME]	AUROC	0.77	—	Unverified
10	XG-HSI-BERT	Accuracy	0.75	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MLARAM	Hamming Loss	0.29	—	Unverified
2	MLkNN	Hamming Loss	0.16	—	Unverified
3	Binary Relevance	Hamming Loss	0.14	—	Unverified
4	Neural Classifier Chains	Hamming Loss	0.13	—	Unverified
5	Neural Binary Relevance	Hamming Loss	0.11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mozafari et al., 2019	AAA	50.94	—	Unverified
2	SVM	AAA	46.51	—	Unverified
3	Kennedy et al., 2020	AAA	45.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HateBERT	Macro F1	0.74	—	Unverified
2	BERT	Macro F1	0.72	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mBert	Accuracy	0.83	—	Unverified
2	Logistic Regression	Accuracy	0.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HXP + CLAP + CLIP	TEST F1 (macro)	0.85	—	Unverified
2	BERT + ViT + MFCC	TEST F1 (macro)	0.79	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HateBERT	Macro F1	0.49	—	Unverified
2	BERT	Macro F1	0.48	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HateBERT	Macro F1	0.81	—	Unverified
2	BERT	Macro F1	0.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Multilingual BERT	F1-score	0.75	—	Unverified
2	AutoML	F1-score	0.74	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AOM mBERT	F1	0.85	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Baseline	F1	0.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-large-ST	Macro F1	80.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Baseline BERT (task A)	F1	0.77	—	Unverified