# BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla

arXiv: https://arxiv.org/abs/2410.13281 · HTML: https://mlsanity.com/paper/2410.13281/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 79 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 27 of 27)

- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [MuRIL: Multilingual Representations for Indian Languages](https://mlsanity.com/paper/2103.10730/) (2021)
- [Multilingual and Multi-Aspect Hate Speech Analysis](https://mlsanity.com/paper/1908.11049/) (2019)
- [BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla](https://mlsanity.com/paper/2101.00204/) (2021)
- [Exploring Hate Speech Detection in Multimodal Publications](https://mlsanity.com/paper/1910.03814/) (2019)
- [Multilingual Offensive Language Identification with Cross-lingual Embeddings](https://mlsanity.com/paper/2010.05324/) (2020)
- [ETHOS: an Online Hate Speech Detection Dataset](https://mlsanity.com/paper/2006.08328/) (2020)
- [Demoting Racial Bias in Hate Speech Detection](https://mlsanity.com/paper/2005.12246/) (2020)
- [Deep Learning Models for Multilingual Hate Speech Detection](https://mlsanity.com/paper/2004.06465/) (2020)
- [Evaluating GPT-3 Generated Explanations for Hateful Content Moderation](https://mlsanity.com/paper/2305.17680/) (2023)
- [From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets](https://mlsanity.com/paper/2404.17874/) (2024)
- [L3Cube-MahaHate: A Tweet-based Marathi Hate Speech Detection Dataset and BERT models](https://mlsanity.com/paper/2203.13778/) (2022)
- [HateCheckHIn: Evaluating Hindi Hate Speech Detection Models](https://mlsanity.com/paper/2205.00328/) (2022)
- [BD-SHS: A Benchmark Dataset for Learning to Detect Online Bangla Hate Speech in Different Social Contexts](https://mlsanity.com/paper/2206.00372/) (2022)
- [K-MHaS: A Multi-label Hate Speech Detection Dataset in Korean Online News Comment](https://mlsanity.com/paper/2208.10684/) (2022)
- [Offensive Language Identification in Transliterated and Code-Mixed Bangla](https://mlsanity.com/paper/2311.15023/) (2023)
- [Improving Counterfactual Generation for Fair Hate Speech Detection](https://mlsanity.com/paper/2108.01721/) (2021)
- [Vacaspati: A Diverse Corpus of Bangla Literature](https://mlsanity.com/paper/2307.05083/) (2023)
- [Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs](https://mlsanity.com/paper/2407.00416/) (2024)
- [Korean Online Hate Speech Dataset for Multilabel Classification: How Can Social Science Improve Dataset on Hate Speech?](https://mlsanity.com/paper/2204.03262/) (2022)
- [Different Strokes for Different Folks: Investigating Appropriate Further Pre-training Approaches for Diverse Dialogue Tasks](https://mlsanity.com/paper/2109.06524/) (2021)

## Built on by (most cited first, 10 of 10)

- [LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target](https://mlsanity.com/paper/2510.01995/) (2025)
- [Read Between the Lines: A Benchmark for Uncovering Political Bias in Bangla News Articles](https://mlsanity.com/paper/2510.03898/) (2025)
- [BIDWESH: A Bangla Regional Based Hate Speech Detection Dataset](https://mlsanity.com/paper/2507.16183/) (2025)
- [Retriv at BLP-2025 Task 1: A Transformer Ensemble and Multi-Task Learning Approach for Bangla Hate Speech Identification](https://mlsanity.com/paper/2511.07304/) (2025)
- [Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration](https://mlsanity.com/paper/2511.22769/) (2025)
- [MixSarc: A Bangla-English Code-Mixed Corpus for Implicit Meaning Identification](https://mlsanity.com/paper/2602.21608/) (2026)
- [MultiSoc-4D: A Benchmark for Diagnosing Instruction-Induced Label Collapse in Closed-Set LLM Annotation of Bengali Social Media](https://mlsanity.com/paper/2605.06940/) (2026)
- [Gradient Masters at BLP-2025 Task 1: Advancing Low-Resource NLP for Bengali using Ensemble-Based Adversarial Training for Hate Speech Detection](https://mlsanity.com/paper/2511.18324/) (2025)
- [5-Dialects-BN: Unmasking the Impact of Transliteration on Bangla Dialectal LLMs](https://mlsanity.com/paper/2609.09964/) (2026)
- [Can LLMs Follow the Pulse of a Crisis? Evaluating Crisis Sentiment in Bangladesh's July Uprising](https://mlsanity.com/paper/2609.16997/) (2026)

## Abstract (arXiv)

The proliferation of transliterated texts in digital spaces has emphasized the need for detecting and classifying hate speech in languages beyond English, particularly in low-resource languages. As online discourse can perpetuate discrimination based on target groups, e.g. gender, religion, and origin, multi-label classification of hateful content can help in comprehending hate motivation and enhance content moderation. While previous efforts have focused on monolingual or binary hate classification tasks, no work has yet addressed the challenge of multi-label hate speech classification in transliterated Bangla. We introduce BanTH, the first multi-label transliterated Bangla hate speech dataset comprising 37.3k samples. The samples are sourced from YouTube comments, where each instance is labeled with one or more target groups, reflecting the regional demographic. We establish novel transformer encoder-based baselines by further pre-training on transliterated Bangla corpus. We also propose a novel translation-based LLM prompting strategy for transliterated text. Experiments reveal that our further pre-trained encoders are achieving state-of-the-art performance on the BanTH dataset, while our translation-based prompting outperforms other strategies in the zero-shot setting. The introduction of BanTH not only fills a critical gap in hate speech research for Bangla but also sets the stage for future exploration into code-mixed and multi-label classification challenges in underrepresented languages.