# Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales arXiv: https://arxiv.org/abs/2403.12403 ยท HTML: https://mlsanity.com/paper/2403.12403/ ## Key facts - Cited by 16 papers in the map (data through 14 Oct 2026). - Builds on 26 of its 44 references that are in the map. - First posted on arXiv 19 Mar 2024. ## Builds on (most cited first, 26 of 26) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019) - [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023) - [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019) - [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018) - [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021) - [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020) - [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022) - [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020) - [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023) - [AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators](https://mlsanity.com/paper/2303.16854/) (2023) - [Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks](https://mlsanity.com/paper/2304.10145/) (2023) - [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) - [Hate Lingo: A Target-based Linguistic Analysis of Hate Speech in Social Media](https://mlsanity.com/paper/1804.04257/) (2018) - [Structured information extraction from complex scientific text with fine-tuned large language models](https://mlsanity.com/paper/2212.05238/) (2022) - ["HOT" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media](https://mlsanity.com/paper/2304.10619/) (2023) - [Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?](https://mlsanity.com/paper/2308.01284/) (2023) - [Improved Text Classification via Contrastive Adversarial Training](https://mlsanity.com/paper/2107.10137/) (2021) - [ConDA: Contrastive Domain Adaptation for AI-generated Text Detection](https://mlsanity.com/paper/2309.03992/) (2023) - [Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost](https://mlsanity.com/paper/2306.15766/) (2023) - [Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability](https://mlsanity.com/paper/2010.13764/) (2020) - [Large Language Models for Propaganda Span Annotation](https://mlsanity.com/paper/2311.09812/) (2023) - [The Price of Interpretability](https://mlsanity.com/paper/1907.03419/) (2019) - [Trusting RoBERTa over BERT: Insights from CheckListing the Natural Language Inference Task](https://mlsanity.com/paper/2107.07229/) (2021) - [PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework](https://mlsanity.com/paper/2306.08804/) (2023) ## Built on by (most cited first, 16 of 16) - [Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning](https://mlsanity.com/paper/2405.15194/) (2024) - [Towards Efficient and Explainable Hate Speech Detection via Model Distillation](https://mlsanity.com/paper/2412.13698/) (2024) - [Self-Explaining Hate Speech Detection with Moral Rationales](https://mlsanity.com/paper/2601.03481/) (2026) - [Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization](https://mlsanity.com/paper/2502.19612/) (2025) - [HateClipSeg: A Segment-Level Annotated Dataset for Fine-Grained Hate Video Detection](https://mlsanity.com/paper/2508.01712/) (2025) - [Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection](https://mlsanity.com/paper/2511.07065/) (2025) - [Argument-Based Consistency in Toxicity Explanations of LLMs](https://mlsanity.com/paper/2506.19113/) (2025) - [Multi-Agent VLMs Guided Self-Training with PNU Loss for Low-Resource Offensive Content Detection](https://mlsanity.com/paper/2511.13759/) (2025) - [StreamSense: Streaming Social Task Detection with Selective Vision-Language Model Routing](https://mlsanity.com/paper/2601.22738/) (2026) - [Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement](https://mlsanity.com/paper/2404.11036/) (2024) - [EdgeAIGuard: Agentic LLMs for Minor Protection in Digital Spaces](https://mlsanity.com/paper/2503.00092/) (2025) - [Ideology-Based LLMs for Content Moderation](https://mlsanity.com/paper/2510.25805/) (2025) - [AggregHate: An Efficient Aggregative Approach for the Detection of Hatemongers on Social Platforms](https://mlsanity.com/paper/2409.14464/) (2024) - [Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?](https://mlsanity.com/paper/2509.22291/) (2025) - [Fine-Grained Perspectives: Modeling Explanations with Annotator-Specific Rationales](https://mlsanity.com/paper/2604.21667/) (2026) - [Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech](https://mlsanity.com/paper/2608.27462/) (2026) ## Abstract (arXiv) Although social media platforms are a prominent arena for users to engage in interpersonal discussions and express opinions, the facade and anonymity offered by social media may allow users to spew hate speech and offensive content. Given the massive scale of such platforms, there arises a need to automatically identify and flag instances of hate speech. Although several hate speech detection methods exist, most of these black-box methods are not interpretable or explainable by design. To address the lack of interpretability, in this paper, we propose to use state-of-the-art Large Language Models (LLMs) to extract features in the form of rationales from the input text, to train a base hate speech classifier, thereby enabling faithful interpretability by design. Our framework effectively combines the textual understanding capabilities of LLMs and the discriminative power of state-of-the-art hate speech classifiers to make these classifiers faithfully interpretable. Our comprehensive evaluation on a variety of English language social media hate speech datasets demonstrate: (1) the goodness of the LLM-extracted rationales, and (2) the surprising retention of detector performance even after training to ensure interpretability. All code and data will be made available at https://github.com/AmritaBh/shield.