A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities
Not on the map. Why?
Abstract (arXiv)
Hate speech online remains an understudied issue for marginalized communities, particularly in the Global South, which includes developing societies with increasing internet penetration. In this paper, we aim to provide marginalized communities in societies where the dominant language is low-resource with a privacy-preserving tool to protect themselves from online hate speech by filtering offensive content in their native languages. Our contributions are twofold: 1) we release REACT (REsponsive hate speech datasets Across ConTexts), a collection of high-quality, culture-specific hate speech detection datasets comprising multiple target groups and low-resource languages, curated by experienced data collectors; 2) we propose a few-shot hate speech detection approach based on federated learning (FL), a privacy-preserving method for collaboratively training a central model that exhibits robustness when tackling different target groups and languages. By keeping training local to user devices, we ensure data privacy while leveraging the collective learning benefits of FL. Furthermore, we explore personalized client models tailored to specific target groups and evaluate their performance. Our findings indicate the overall effectiveness of FL across different target groups, and point to personalization as a promising direction.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 38 of its 64 references that are in the map. First posted on arXiv 6 Dec 2024.
Builds on
38 of 64 references.
References · 38
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
- 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
- 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,167
26 more
- 2019Towards Federated Learning at Scale: System Designcited by 832
- 2018Federated Learning for Mobile Keyboard Predictioncited by 572
- 2019Federated Learning with Personalization Layerscited by 541
- 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 380
- 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 285
- 2020HateCheck: Functional Tests for Hate Speech Detection Modelscited by 216
- 2016Ex Machina: Personal Attacks Seen at Scalecited by 210
- 2019Racial Bias in Hate Speech and Abusive Language Detection Datasetscited by 209
- 2020HateBERT: Retraining BERT for Abusive Language Detection in Englishcited by 207
- 2019A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Mediacited by 96
- 2023When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Taskscited by 90
- 2020Chasing Carbon: The Elusive Environmental Footprint of Computingcited by 72
- 2022Handling Bias in Toxic Speech Detection: A Surveycited by 61
- 2020Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applicationscited by 58
- 2022Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Modelscited by 51
- 2020Offensive Language Identification in Greekcited by 50
- 2021Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detectioncited by 45
- 2021MUDES: Multilingual Detection of Offensive Spanscited by 30
- 2021FBERT: A Neural Transformer for Identifying Offensive Contentcited by 30
- 2021Multilingual Offensive Language Identification for Low-resource Languagescited by 22
- 2022Listening to Affected Communities to Define Extreme Speech: Dataset and Experimentscited by 22
- 2023Toxic Bias: Perspective API Misreads German as More Toxiccited by 21
- 2022Hate Speech and Offensive Language Detection in Bengalicited by 19
- 2020Characterizing Twitter Users Who Engage in Adversarial Interactions against Political Candidatescited by 6
- 2024A Federated Learning Approach to Privacy Preserving Offensive Language Identificationcited by 4
- 2023A Federated Approach for Hate Speech Detectioncited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.