# Multilingual and Explainable Text Detoxification with Parallel Corpora

arXiv: https://arxiv.org/abs/2412.11691 · HTML: https://mlsanity.com/paper/2412.11691/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 78 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 30 of 39)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Deep Learning for Text Style Transfer: A Survey](https://mlsanity.com/paper/2011.00416/) (2020)
- [Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis](https://mlsanity.com/paper/1701.08118/) (2017)
- [Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer](https://mlsanity.com/paper/1805.07685/) (2018)
- [XFORMAL: A Benchmark for Multilingual Formality Style Transfer](https://mlsanity.com/paper/2104.04108/) (2021)
- [Text Detoxification using Large Pre-trained Neural Models](https://mlsanity.com/paper/2109.08914/) (2021)
- [Probing LLMs for hate speech detection: strengths and vulnerabilities](https://mlsanity.com/paper/2310.12860/) (2023)
- [Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://mlsanity.com/paper/2305.04446/) (2023)
- [Self-Detoxifying Language Models via Toxification Reversal](https://mlsanity.com/paper/2310.09573/) (2023)
- [SWSR: A Chinese Dataset and Lexicon for Online Sexism Detection](https://mlsanity.com/paper/2108.03070/) (2021)
- [Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts](https://mlsanity.com/paper/2212.10543/) (2022)
- [Artificial Intelligence for Social Good: A Survey](https://mlsanity.com/paper/2001.01818/) (2020)
- [Evaluating prose style transfer with the Bible](https://mlsanity.com/paper/1711.04731/) (2017)
- [APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations](https://mlsanity.com/paper/2209.08207/) (2022)
- [RoBERTuito: a pre-trained language model for social media text in Spanish](https://mlsanity.com/paper/2111.09453/) (2021)
- [ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer](https://mlsanity.com/paper/2308.15459/) (2023)
- [Let-Mi: An Arabic Levantine Twitter Dataset for Misogynistic Language](https://mlsanity.com/paper/2103.10195/) (2021)
- [Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification](https://mlsanity.com/paper/2311.13937/) (2023)
- [MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector](https://mlsanity.com/paper/2401.05060/) (2024)

## Built on by (most cited first, 12 of 12)

- [SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators](https://mlsanity.com/paper/2502.06394/) (2025)
- [Translate, then Detect: Leveraging Machine Translation for Cross-Lingual Toxicity Classification](https://mlsanity.com/paper/2509.14493/) (2025)
- [Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification](https://mlsanity.com/paper/2505.16722/) (2025)
- [Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection](https://mlsanity.com/paper/2511.07065/) (2025)
- [Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites](https://mlsanity.com/paper/2505.15297/) (2025)
- [HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation](https://mlsanity.com/paper/2507.04350/) (2025)
- [BanglaNirTox: A Large-scale Parallel Corpus for Explainable AI in Bengali Text Detoxification](https://mlsanity.com/paper/2511.01512/) (2025)
- [Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure](https://mlsanity.com/paper/2604.25580/) (2026)
- [GemDetox at TextDetox CLEF 2025: Enhancing a Massively Multilingual Model for Text Detoxification on Low-resource Languages](https://mlsanity.com/paper/2510.01250/) (2025)
- [RT-SFT: Text Style Transfer from Non-Parallel Corpora by Roundtrip Translation](https://mlsanity.com/paper/2602.15013/) (2026)
- [A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models](https://mlsanity.com/paper/2606.25380/) (2026)
- [From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation](https://mlsanity.com/paper/2608.25605/) (2026)

## Abstract (arXiv)

Even with various regulations in place across countries and social media platforms (Government of India, 2021; European Parliament and Council of the European Union, 2022, digital abusive speech remains a significant issue. One potential approach to address this challenge is automatic text detoxification, a text style transfer (TST) approach that transforms toxic language into a more neutral or non-toxic form. To date, the availability of parallel corpora for the text detoxification task (Logachevavet al., 2022; Atwell et al., 2022; Dementievavet al., 2024a) has proven to be crucial for state-of-the-art approaches. With this work, we extend parallel text detoxification corpus to new languages -- German, Chinese, Arabic, Hindi, and Amharic -- testing in the extensive multilingual setup TST baselines. Next, we conduct the first of its kind an automated, explainable analysis of the descriptive features of both toxic and non-toxic sentences, diving deeply into the nuances, similarities, and differences of toxicity and detoxification across 9 languages. Finally, based on the obtained insights, we experiment with a novel text detoxification method inspired by the Chain-of-Thoughts reasoning approach, enhancing the prompting process through clustering on relevant descriptive attributes.