# A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings

arXiv: https://arxiv.org/abs/2505.12116 · HTML: https://mlsanity.com/paper/2505.12116/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 70 references that are in the map.
- First posted on arXiv 17 May 2025.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://mlsanity.com/paper/1903.08983/) (2019)
- [SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects](https://mlsanity.com/paper/2309.07445/) (2023)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model](https://mlsanity.com/paper/2008.06460/) (2020)
- [Aggression-annotated Corpus of Hindi-English Code-mixed Data](https://mlsanity.com/paper/1803.09402/) (2018)
- [A Unified Deep Learning Architecture for Abuse Detection](https://mlsanity.com/paper/1802.00385/) (2018)
- [Automatic Detection of Cyberbullying in Social Media Text](https://mlsanity.com/paper/1801.05617/) (2018)
- [Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models](https://mlsanity.com/paper/2312.08303/) (2023)
- [Joint Modelling of Emotion and Abusive Language Detection](https://mlsanity.com/paper/2005.14028/) (2020)
- [Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection](https://mlsanity.com/paper/2004.13432/) (2020)
- [Detect All Abuse! Toward Universal Abusive Language Detection Models](https://mlsanity.com/paper/2010.03776/) (2020)
- [AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages](https://mlsanity.com/paper/2501.08284/) (2025)
- [NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Data](https://mlsanity.com/paper/2403.19260/) (2024)
- [Transferring Monolingual Model to Low-Resource Language: The Case of Tigrinya](https://mlsanity.com/paper/2006.07698/) (2020)
- [An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation](https://mlsanity.com/paper/2103.16789/) (2021)
- [Tigrinya Neural Machine Translation with Transfer Learning for Humanitarian Response](https://mlsanity.com/paper/2003.11523/) (2020)
- [Hate Speech and Offensive Language Detection using an Emotion-aware Shared Encoder](https://mlsanity.com/paper/2302.08777/) (2023)

## Built on by (most cited first, 1 of 1)

- [Natural Language Processing for Tigrinya: Current State and Future Directions](https://mlsanity.com/paper/2507.17974/) (2025)

## Abstract (arXiv)

Content moderation research has recently made significant advances, but remains limited in serving the majority of the world's languages due to the lack of resources, leaving millions of vulnerable users to online hostility. This work presents a large-scale human-annotated multi-task benchmark dataset for abusive language detection in Tigrinya social media with joint annotations for three tasks: abusiveness, sentiment, and topic classification. The dataset comprises 13,717 YouTube comments annotated by nine native speakers, collected from 7,373 videos with a total of over 1.2 billion views across 51 channels. We developed an iterative term clustering approach for effective data selection. Recognizing that around 64% of Tigrinya social media content uses Romanized transliterations rather than native Ge'ez script, our dataset accommodates both writing systems to reflect actual language use. We establish strong baselines across the tasks in the benchmark, while leaving significant challenges for future contributions. Our experiments demonstrate that small fine-tuned models outperform prompted frontier large language models (LLMs) in the low-resource setting, achieving 86.67% F1 in abusiveness detection (7+ points over best LLM), and maintain stronger performance in all other tasks. The benchmark is made public to promote research on online safety.