# Mitigating Text Toxicity with Counterfactual Generation

arXiv: https://arxiv.org/abs/2405.09948 · HTML: https://mlsanity.com/paper/2405.09948/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 67 references that are in the map.
- First posted on arXiv 16 May 2024.

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [FACE: Feasible and Actionable Counterfactual Explanations](https://mlsanity.com/paper/1909.09369/) (2019)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Explaining NLP Models via Minimal Contrastive Editing (MiCE)](https://mlsanity.com/paper/2012.13985/) (2020)
- [The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations](https://mlsanity.com/paper/1907.09294/) (2019)
- [Beyond BLEU: Training Neural Machine Translation with Semantic Similarity](https://mlsanity.com/paper/1909.06694/) (2019)
- [Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer](https://mlsanity.com/paper/1805.07685/) (2018)
- [Text Detoxification using Large Pre-trained Neural Models](https://mlsanity.com/paper/2109.08914/) (2021)
- [Combining Generative Artificial Intelligence (AI) and the Internet: Heading towards Evolution or Degradation?](https://mlsanity.com/paper/2303.01255/) (2023)
- [Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts](https://mlsanity.com/paper/2212.10543/) (2022)
- [Civil Rephrases Of Toxic Texts With Self-Supervised Transformers](https://mlsanity.com/paper/2102.05456/) (2021)
- [CREST: A Joint Framework for Rationalization and Counterfactual Text Generation](https://mlsanity.com/paper/2305.17075/) (2023)
- [A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data](https://mlsanity.com/paper/2107.04680/) (2021)
- [Personalizing Content Moderation on Social Media: User Perspectives on Moderation Choices, Interface Design, and Labor](https://mlsanity.com/paper/2305.10374/) (2023)
- [Towards A Friendly Online Community: An Unsupervised Style Transfer Framework for Profanity Redaction](https://mlsanity.com/paper/2011.00403/) (2020)
- [Text Counterfactuals via Latent Optimization and Shapley-Guided Search](https://mlsanity.com/paper/2110.11589/) (2021)

## Built on by (most cited first, 2 of 2)

- [Generative Data Refinement: Just Ask for Better Data](https://mlsanity.com/paper/2509.08653/) (2025)
- [Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions](https://mlsanity.com/paper/2509.25539/) (2025)

## Abstract (arXiv)

Toxicity mitigation consists in rephrasing text in order to remove offensive or harmful meaning. Neural natural language processing (NLP) models have been widely used to target and mitigate textual toxicity. However, existing methods fail to detoxify text while preserving the initial non-toxic meaning at the same time. In this work, we propose to apply counterfactual generation methods from the eXplainable AI (XAI) field to target and mitigate textual toxicity. In particular, we perform text detoxification by applying local feature importance and counterfactual generation methods to a toxicity classifier distinguishing between toxic and non-toxic texts. We carry out text detoxification through counterfactual generation on three datasets and compare our approach to three competitors. Automatic and human evaluations show that recently developed NLP counterfactual generators can mitigate toxicity accurately while better preserving the meaning of the initial text as compared to classical detoxification methods. Finally, we take a step back from using automated detoxification tools, and discuss how to manage the polysemous nature of toxicity and the risk of malicious use of detoxification tools. This work is the first to bridge the gap between counterfactual generation and text detoxification and paves the way towards more practical application of XAI methods.