# BanglaNirTox: A Large-scale Parallel Corpus for Explainable AI in Bengali Text Detoxification

arXiv: https://arxiv.org/abs/2511.01512 · HTML: https://mlsanity.com/paper/2511.01512/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 3 Nov 2025.

## Builds on (most cited first, 15 of 15)

- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla](https://mlsanity.com/paper/2205.11081/) (2022)
- [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)
- [Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network](https://mlsanity.com/paper/2004.07807/) (2020)
- [APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations](https://mlsanity.com/paper/2209.08207/) (2022)
- [Towards A Friendly Online Community: An Unsupervised Style Transfer Framework for Profanity Redaction](https://mlsanity.com/paper/2011.00403/) (2020)
- [BD-SHS: A Benchmark Dataset for Learning to Detect Online Bangla Hate Speech in Different Social Contexts](https://mlsanity.com/paper/2206.00372/) (2022)
- [MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages](https://mlsanity.com/paper/2404.02037/) (2024)
- [Methods for Detoxification of Texts for the Russian Language](https://mlsanity.com/paper/2105.09052/) (2021)
- [Multilingual and Explainable Text Detoxification with Parallel Corpora](https://mlsanity.com/paper/2412.11691/) (2024)
- [Text Detoxification as Style Transfer in English and Hindi](https://mlsanity.com/paper/2402.07767/) (2024)
- [Bangla hate speech detection on social media using attention-based recurrent neural network](https://mlsanity.com/paper/2203.16775/) (2022)
- [ToxVis: Enabling Interpretability of Implicit vs. Explicit Toxicity Detection Models with Interactive Visualization](https://mlsanity.com/paper/2303.09402/) (2023)

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

- [The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar](https://mlsanity.com/paper/2606.26015/) (2026)

## Abstract (arXiv)

Toxic language in Bengali remains prevalent, especially in online environments, with few effective precautions against it. Although text detoxification has seen progress in high-resource languages, Bengali remains underexplored due to limited resources. In this paper, we propose a novel pipeline for Bengali text detoxification that combines Pareto class-optimized large language models (LLMs) and Chain-of-Thought (CoT) prompting to generate detoxified sentences. To support this effort, we construct BanglaNirTox, an artificially generated parallel corpus of 68,041 toxic Bengali sentences with class-wise toxicity labels, reasonings, and detoxified paraphrases, using Pareto-optimized LLMs evaluated on random samples. The resulting BanglaNirTox dataset is used to fine-tune language models to produce better detoxified versions of Bengali sentences. Our findings show that Pareto-optimized LLMs with CoT prompting significantly enhance the quality and consistency of Bengali text detoxification.