# Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization

arXiv: https://arxiv.org/abs/2309.02311 · HTML: https://mlsanity.com/paper/2309.02311/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 5 Sep 2023.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization](https://mlsanity.com/paper/1911.03437/) (2019)
- [Why We Need New Evaluation Metrics for NLG](https://mlsanity.com/paper/1707.06875/) (2017)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [Better Fine-Tuning by Reducing Representational Collapse](https://mlsanity.com/paper/2008.03156/) (2020)
- [A Benchmark Dataset for Learning to Intervene in Online Hate Speech](https://mlsanity.com/paper/1909.04251/) (2019)
- [Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech](https://mlsanity.com/paper/2107.08720/) (2021)
- [Generating Counter Narratives against Online Hate Speech: Data and Strategies](https://mlsanity.com/paper/2004.04216/) (2020)
- [Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists](https://mlsanity.com/paper/2203.09192/) (2022)
- [How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?](https://mlsanity.com/paper/2112.11668/) (2021)
- [Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech](https://mlsanity.com/paper/2106.01625/) (2021)
- [Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech](https://mlsanity.com/paper/2106.11783/) (2021)
- [Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering](https://mlsanity.com/paper/2211.03433/) (2022)
- [Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study](https://mlsanity.com/paper/2204.01440/) (2022)
- [CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech](https://mlsanity.com/paper/2205.04304/) (2022)

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

- [NLP for Counterspeech against Hate: A Survey and How-To Guide](https://mlsanity.com/paper/2403.20103/) (2024)
- [Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation](https://mlsanity.com/paper/2405.16504/) (2024)
- [Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering](https://mlsanity.com/paper/2410.03466/) (2024)
- [A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot LLM Classification Performance](https://mlsanity.com/paper/2506.18576/) (2025)
- [A Multi-Aspect Framework for Counter Narrative Evaluation using Large Language Models](https://mlsanity.com/paper/2402.11676/) (2024)
- [Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation](https://mlsanity.com/paper/2510.12316/) (2025)
- [Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeech](https://mlsanity.com/paper/2508.04638/) (2025)

## Abstract (arXiv)

Recent computational approaches for combating online hate speech involve the automatic generation of counter narratives by adapting Pretrained Transformer-based Language Models (PLMs) with human-curated data. This process, however, can produce in-domain overfitting, resulting in models generating acceptable narratives only for hatred similar to training data, with little portability to other targets or to real-world toxic language. This paper introduces novel attention regularization methodologies to improve the generalization capabilities of PLMs for counter narratives generation. Overfitting to training-specific terms is then discouraged, resulting in more diverse and richer narratives. We experiment with two attention-based regularization techniques on a benchmark English dataset. Regularized models produce better counter narratives than state-of-the-art approaches in most cases, both in terms of automatic metrics and human evaluation, especially when hateful targets are not present in the training data. This work paves the way for better and more flexible counter-speech generation models, a task for which datasets are highly challenging to produce.