# AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection

arXiv: https://arxiv.org/abs/2505.19528 · HTML: https://mlsanity.com/paper/2505.19528/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [Why do LLMs attend to the first token?](https://mlsanity.com/paper/2504.02732/) (2025)
- [Word Embeddings Are Steers for Language Models](https://mlsanity.com/paper/2305.12798/) (2023)
- [Demoting Racial Bias in Hate Speech Detection](https://mlsanity.com/paper/2005.12246/) (2020)
- [Recognizing Explicit and Implicit Hate Speech Using a Weakly Supervised Two-path Bootstrapping Approach](https://mlsanity.com/paper/1710.07394/) (2017)
- [A Web of Hate: Tackling Hateful Speech in Online Social Spaces](https://mlsanity.com/paper/1709.10159/) (2017)
- [Target Span Detection for Implicit Harmful Content](https://mlsanity.com/paper/2403.19836/) (2024)
- [Hate Speech Detection with Generalizable Target-aware Fairness](https://mlsanity.com/paper/2406.00046/) (2024)
- [DefVerify: Do Hate Speech Models Reflect Their Dataset's Definition?](https://mlsanity.com/paper/2410.15911/) (2024)
- [Please, Don't Forget the Difference and the Confidence Interval when Seeking for the State-of-the-Art Status](https://mlsanity.com/paper/2205.11134/) (2022)
- [Student's t-Distribution: On Measuring the Inter-Rater Reliability When the Observations are Scarce](https://mlsanity.com/paper/2303.04526/) (2023)

## Built on by (most cited first, 1 of 1)

- [RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection](https://mlsanity.com/paper/2510.10971/) (2025)

## Abstract (arXiv)

Implicit hate speech detection is challenging due to its subtlety and reliance on contextual interpretation rather than explicit offensive words. Current approaches rely on contrastive learning, which are shown to be effective on distinguishing hate and non-hate sentences. Humans, however, detect implicit hate speech by first identifying specific targets within the text and subsequently interpreting how these target relate to their surrounding context. Motivated by this reasoning process, we propose AmpleHate, a novel approach designed to mirror human inference for implicit hate detection. AmpleHate identifies explicit target using a pretrained Named Entity Recognition model and capture implicit target information via [CLS] tokens. It computes attention-based relationships between explicit, implicit targets and sentence context and then, directly injects these relational vectors into the final sentence representation. This amplifies the critical signals of target-context relations for determining implicit hate. Experiments demonstrate that AmpleHate achieves state-of-the-art performance, outperforming contrastive learning baselines by an average of 82.14% and achieve faster convergence. Qualitative analyses further reveal that attention patterns produced by AmpleHate closely align with human judgement, underscoring its interpretability and robustness. Our code is publicly available at: https://github.com/leeyejin1231/AmpleHate.