# DefVerify: Do Hate Speech Models Reflect Their Dataset's Definition?

arXiv: https://arxiv.org/abs/2410.15911 · HTML: https://mlsanity.com/paper/2410.15911/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 56 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 23 of 23)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [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)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [MultiVerS: Improving scientific claim verification with weak supervision and full-document context](https://mlsanity.com/paper/2112.01640/) (2021)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis](https://mlsanity.com/paper/1701.08118/) (2017)
- [Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning](https://mlsanity.com/paper/2009.10277/) (2020)
- [Challenges for Toxic Comment Classification: An In-Depth Error Analysis](https://mlsanity.com/paper/1809.07572/) (2018)
- [Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models](https://mlsanity.com/paper/2206.09917/) (2022)
- [A Framework for the Computational Linguistic Analysis of Dehumanization](https://mlsanity.com/paper/2003.03014/) (2020)
- [FBERT: A Neural Transformer for Identifying Offensive Content](https://mlsanity.com/paper/2109.05074/) (2021)
- [Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation](https://mlsanity.com/paper/2307.01680/) (2023)
- [How Hate Speech Varies by Target Identity: A Computational Analysis](https://mlsanity.com/paper/2210.10839/) (2022)
- [Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions](https://mlsanity.com/paper/2206.15455/) (2022)
- [Detecting weak and strong Islamophobic hate speech on social media](https://mlsanity.com/paper/1812.10400/) (2018)
- [On Analyzing Annotation Consistency in Online Abusive Behavior Datasets](https://mlsanity.com/paper/2006.13507/) (2020)

## Built on by (most cited first, 7 of 7)

- [Something Just Like TRuST : Toxicity Recognition of Span and Target](https://mlsanity.com/paper/2506.02326/) (2025)
- [AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection](https://mlsanity.com/paper/2505.19528/) (2025)
- [Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification](https://mlsanity.com/paper/2601.08668/) (2026)
- [Tell Me What You Know About Sexism: Expert-LLM Interaction Strategies and Co-Created Definitions for Zero-Shot Sexism Detection](https://mlsanity.com/paper/2504.15392/) (2025)
- [RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection](https://mlsanity.com/paper/2510.10971/) (2025)
- [Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining](https://mlsanity.com/paper/2607.23175/) (2026)
- [To Jev or Not? Evaluating the Accuracy and Efficiency of Structured Decision Models for Hate-Speech Moderation](https://mlsanity.com/paper/2610.03324/) (2026)

## Abstract (arXiv)

When building a predictive model, it is often difficult to ensure that application-specific requirements are encoded by the model that will eventually be deployed. Consider researchers working on hate speech detection. They will have an idea of what is considered hate speech, but building a model that reflects their view accurately requires preserving those ideals throughout the workflow of data set construction and model training. Complications such as sampling bias, annotation bias, and model misspecification almost always arise, possibly resulting in a gap between the application specification and the model's actual behavior upon deployment. To address this issue for hate speech detection, we propose DefVerify: a 3-step procedure that (i) encodes a user-specified definition of hate speech, (ii) quantifies to what extent the model reflects the intended definition, and (iii) tries to identify the point of failure in the workflow. We use DefVerify to find gaps between definition and model behavior when applied to six popular hate speech benchmark datasets.