# Explain the Flag: Contextualizing Hate Speech Beyond Censorship

arXiv: https://arxiv.org/abs/2604.14970 · HTML: https://mlsanity.com/paper/2604.14970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [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)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Multilingual and Multi-Aspect Hate Speech Analysis](https://mlsanity.com/paper/1908.11049/) (2019)
- [Contextualizing Hate Speech Classifiers with Post-hoc Explanation](https://mlsanity.com/paper/2005.02439/) (2020)
- [Demoting Racial Bias in Hate Speech Detection](https://mlsanity.com/paper/2005.12246/) (2020)
- [Hate Lingo: A Target-based Linguistic Analysis of Hate Speech in Social Media](https://mlsanity.com/paper/1804.04257/) (2018)
- [Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting](https://mlsanity.com/paper/2004.14088/) (2020)
- [Detecting East Asian Prejudice on Social Media](https://mlsanity.com/paper/2005.03909/) (2020)
- [Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech](https://mlsanity.com/paper/2209.04889/) (2022)
- [From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets](https://mlsanity.com/paper/2404.17874/) (2024)
- [A Dictionary-based Approach to Racism Detection in Dutch Social Media](https://mlsanity.com/paper/1608.08738/) (2016)
- [Leveraging Affective Bidirectional Transformers for Offensive Language Detection](https://mlsanity.com/paper/2006.01266/) (2020)
- [Context-Aware Attention for Understanding Twitter Abuse](https://mlsanity.com/paper/1809.08726/) (2018)
- [Do explanations increase the effectiveness of AI-crowd generated fake news warnings?](https://mlsanity.com/paper/2112.03450/) (2021)
- [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)
- [Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections](https://mlsanity.com/paper/2505.24538/) (2025)

## Abstract (arXiv)

Hate, derogatory, and offensive speech remains a persistent challenge in online platforms and public discourse. While automated detection systems are widely used, most focus on censorship or removal, raising concerns for transparency and freedom of expression, and limiting opportunities to explain why content is harmful. To address these issues, explanatory approaches have emerged as a promising solution, aiming to make hate speech detection more transparent, accountable, and informative. In this paper, we present a hybrid approach that combines Large Language Models (LLMs) with three newly created and curated vocabularies to detect and explain hate speech in English, French, and Greek. Our system captures both inherently derogatory expressions tied to identity characteristics and direct group-targeted content through two complementary pipelines: one that detects and disambiguates problematic terms using the curated vocabularies, and one that leverages LLMs as context-aware evaluators of group-targeting content. The outputs are fused into grounded explanations that clarify why content is flagged. Human evaluation shows that our hybrid approach is accurate, with high-quality explanations, outperforming LLM-only baselines.