# ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection

arXiv: https://arxiv.org/abs/2205.12495 · HTML: https://mlsanity.com/paper/2205.12495/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 25 May 2022.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 18 of 18)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Predicting the Type and Target of Offensive Posts in Social Media](https://mlsanity.com/paper/1902.09666/) (2019)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [Jury Learning: Integrating Dissenting Voices into Machine Learning Models](https://mlsanity.com/paper/2202.02950/) (2022)
- [Cross-lingual Zero- and Few-shot Hate Speech Detection Utilising Frozen Transformer Language Models and AXEL](https://mlsanity.com/paper/2004.13850/) (2020)
- [Preserving Integrity in Online Social Networks](https://mlsanity.com/paper/2009.10311/) (2020)
- [An Information Retrieval Approach to Building Datasets for Hate Speech Detection](https://mlsanity.com/paper/2106.09775/) (2021)
- [Annotating for Hate Speech: The MaNeCo Corpus and Some Input from Critical Discourse Analysis](https://mlsanity.com/paper/2008.06222/) (2020)
- [Meta AI at Arabic Hate Speech 2022: MultiTask Learning with Self-Correction for Hate Speech Classification](https://mlsanity.com/paper/2205.07960/) (2022)

## Built on by (most cited first, 15 of 15)

- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://mlsanity.com/paper/2305.04446/) (2023)
- [HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning](https://mlsanity.com/paper/2311.00321/) (2023)
- [Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2312.15099/) (2023)
- [Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech](https://mlsanity.com/paper/2406.03953/) (2024)
- [Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment](https://mlsanity.com/paper/2306.01105/) (2023)
- [Hypothesis Engineering for Zero-Shot Hate Speech Detection](https://mlsanity.com/paper/2210.00910/) (2022)
- [Towards Legally Enforceable Hate Speech Detection for Public Forums](https://mlsanity.com/paper/2305.13677/) (2023)
- [Hate Speech Detection via Dual Contrastive Learning](https://mlsanity.com/paper/2307.05578/) (2023)
- [Conditioning Large Language Models on Legal Systems? Detecting Punishable Hate Speech](https://mlsanity.com/paper/2506.03009/) (2025)
- [Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks](https://mlsanity.com/paper/2507.11292/) (2025)
- [Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse](https://mlsanity.com/paper/2401.14616/) (2024)
- [A Group-Specific Approach to NLP for Hate Speech Detection](https://mlsanity.com/paper/2304.11223/) (2023)
- [U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario](https://mlsanity.com/paper/2501.00907/) (2025)
- [Selective Demonstration Retrieval for Improved Implicit Hate Speech Detection](https://mlsanity.com/paper/2504.12082/) (2025)

## Abstract (arXiv)

Hate speech detection is complex; it relies on commonsense reasoning, knowledge of stereotypes, and an understanding of social nuance that differs from one culture to the next. It is also difficult to collect a large-scale hate speech annotated dataset. In this work, we frame this problem as a few-shot learning task, and show significant gains with decomposing the task into its "constituent" parts. In addition, we see that infusing knowledge from reasoning datasets (e.g. Atomic2020) improves the performance even further. Moreover, we observe that the trained models generalize to out-of-distribution datasets, showing the superiority of task decomposition and knowledge infusion compared to previously used methods. Concretely, our method outperforms the baseline by 17.83% absolute gain in the 16-shot case.