# Text Detoxification as Style Transfer in English and Hindi

arXiv: https://arxiv.org/abs/2402.07767 · HTML: https://mlsanity.com/paper/2402.07767/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 50 references that are in the map.
- First posted on arXiv 12 Feb 2024.

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

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [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)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Why We Need New Evaluation Metrics for NLG](https://mlsanity.com/paper/1707.06875/) (2017)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Style Transfer in Text: Exploration and Evaluation](https://mlsanity.com/paper/1711.06861/) (2017)
- [mGPT: Few-Shot Learners Go Multilingual](https://mlsanity.com/paper/2204.07580/) (2022)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [Evaluating Style Transfer for Text](https://mlsanity.com/paper/1904.02295/) (2019)
- [Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models](https://mlsanity.com/paper/1707.01161/) (2017)
- [Text Detoxification using Large Pre-trained Neural Models](https://mlsanity.com/paper/2109.08914/) (2021)
- [SemEval-2023 Task 11: Learning With Disagreements (LeWiDi)](https://mlsanity.com/paper/2304.14803/) (2023)
- [Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings](https://mlsanity.com/paper/2110.07385/) (2021)
- [The ComMA Dataset V0.2: Annotating Aggression and Bias in Multilingual Social Media Discourse](https://mlsanity.com/paper/2111.10390/) (2021)

## Built on by (most cited first, 11 of 11)

- [Style-Specific Neurons for Steering LLMs in Text Style Transfer](https://mlsanity.com/paper/2410.00593/) (2024)
- [Are Large Language Models Actually Good at Text Style Transfer?](https://mlsanity.com/paper/2406.05885/) (2024)
- [Multilingual Text Style Transfer: Datasets & Models for Indian Languages](https://mlsanity.com/paper/2405.20805/) (2024)
- [Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?](https://mlsanity.com/paper/2502.04718/) (2025)
- [Text Style Transfer: An Introductory Overview](https://mlsanity.com/paper/2407.14822/) (2024)
- [Steering Large Language Models with Register Analysis for Arbitrary Style Transfer](https://mlsanity.com/paper/2505.00679/) (2025)
- [Evaluating Text Style Transfer: A Nine-Language Benchmark for Text Detoxification](https://mlsanity.com/paper/2507.15557/) (2025)
- [Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification](https://mlsanity.com/paper/2505.16722/) (2025)
- [BanglaNirTox: A Large-scale Parallel Corpus for Explainable AI in Bengali Text Detoxification](https://mlsanity.com/paper/2511.01512/) (2025)
- [Text Detoxification in isiXhosa and Yor`ub'a: A Cross-Lingual Machine Learning Approach for Low-Resource African Languages](https://mlsanity.com/paper/2601.05624/) (2026)
- [A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models](https://mlsanity.com/paper/2606.25380/) (2026)

## Abstract (arXiv)

This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where the text style changes while its content is preserved. We present three approaches: knowledge transfer from a similar task, multi-task learning approach, combining sequence-to-sequence modeling with various toxicity classification tasks, and delete and reconstruct approach. To support our research, we utilize a dataset provided by Dementieva et al.(2021), which contains multiple versions of detoxified texts corresponding to toxic texts. In our experiments, we selected the best variants through expert human annotators, creating a dataset where each toxic sentence is paired with a single, appropriate detoxified version. Additionally, we introduced a small Hindi parallel dataset, aligning with a part of the English dataset, suitable for evaluation purposes. Our results demonstrate that our approach effectively balances text detoxication while preserving the actual content and maintaining fluency.