# Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection

arXiv: https://arxiv.org/abs/2205.03302 · HTML: https://mlsanity.com/paper/2205.03302/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 48 references that are in the map.
- First posted on arXiv 6 May 2022.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [Reducing Gender Bias in Abusive Language Detection](https://mlsanity.com/paper/1808.07231/) (2018)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)
- [Enabling Language Models to Fill in the Blanks](https://mlsanity.com/paper/2005.05339/) (2020)
- [Explaining NLP Models via Minimal Contrastive Editing (MiCE)](https://mlsanity.com/paper/2012.13985/) (2020)
- [The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations](https://mlsanity.com/paper/2106.00786/) (2021)
- [Aligning Faithful Interpretations with their Social Attribution](https://mlsanity.com/paper/2006.01067/) (2020)
- [Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End](https://mlsanity.com/paper/2011.04917/) (2020)
- [Explaining The Efficacy of Counterfactually Augmented Data](https://mlsanity.com/paper/2010.02114/) (2020)

## Built on by (most cited first, 18 of 18)

- [Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models](https://mlsanity.com/paper/2401.16727/) (2024)
- [Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models](https://mlsanity.com/paper/2206.03945/) (2022)
- [Towards Trustworthy Explanation: On Causal Rationalization](https://mlsanity.com/paper/2306.14115/) (2023)
- [Explainable Abuse Detection as Intent Classification and Slot Filling](https://mlsanity.com/paper/2210.02659/) (2022)
- [InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations](https://mlsanity.com/paper/2310.05592/) (2023)
- [Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech](https://mlsanity.com/paper/2406.03953/) (2024)
- [Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information](https://mlsanity.com/paper/2210.10689/) (2022)
- [Mechanistic Interpretability Needs Philosophy](https://mlsanity.com/paper/2506.18852/) (2025)
- [Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers](https://mlsanity.com/paper/2307.01900/) (2023)
- [Probing Critical Learning Dynamics of PLMs for Hate Speech Detection](https://mlsanity.com/paper/2402.02144/) (2024)
- [Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models](https://mlsanity.com/paper/2305.18585/) (2023)
- [Unifying Formal Explanations: A Complexity-Theoretic Perspective](https://mlsanity.com/paper/2602.18160/) (2026)
- [ERAS: Evaluating the Robustness of Chinese NLP Models to Morphological Garden Path Errors](https://mlsanity.com/paper/2410.13057/) (2024)
- [Promoting Security and Trust on Social Networks: Explainable Cyberbullying Detection Using Large Language Models in a Stream-Based Machine Learning Framework](https://mlsanity.com/paper/2505.03746/) (2025)
- [Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity](https://mlsanity.com/paper/2509.09794/) (2025)
- [Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence](https://mlsanity.com/paper/2609.05385/) (2026)
- [Regional Explanations via Causal Sufficiency and Necessity](https://mlsanity.com/paper/2609.18049/) (2026)
- [Does a model's stated reason for rejecting a candidate do any work?](https://mlsanity.com/paper/2609.30151/) (2026)

## Abstract (arXiv)

We present a novel feature attribution method for explaining text classifiers, and analyze it in the context of hate speech detection. Although feature attribution models usually provide a single importance score for each token, we instead provide two complementary and theoretically-grounded scores -- necessity and sufficiency -- resulting in more informative explanations. We propose a transparent method that calculates these values by generating explicit perturbations of the input text, allowing the importance scores themselves to be explainable. We employ our method to explain the predictions of different hate speech detection models on the same set of curated examples from a test suite, and show that different values of necessity and sufficiency for identity terms correspond to different kinds of false positive errors, exposing sources of classifier bias against marginalized groups.