# Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation

arXiv: https://arxiv.org/abs/2311.06532 · HTML: https://mlsanity.com/paper/2311.06532/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 11 Nov 2023.

## Builds on (most cited first, 10 of 10)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [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)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer](https://mlsanity.com/paper/2205.11631/) (2022)
- [Toxicity in Multilingual Machine Translation at Scale](https://mlsanity.com/paper/2210.03070/) (2022)
- [BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric](https://mlsanity.com/paper/2212.08486/) (2022)
- [DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances](https://mlsanity.com/paper/2110.07592/) (2021)
- [ReSeTOX: Re-learning attention weights for toxicity mitigation in machine translation](https://mlsanity.com/paper/2305.11761/) (2023)

## Built on by (most cited first, 5 of 5)

- [From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models](https://mlsanity.com/paper/2403.03893/) (2024)
- [Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification](https://mlsanity.com/paper/2505.16722/) (2025)
- [Towards Massive Multilingual Holistic Bias](https://mlsanity.com/paper/2407.00486/) (2024)
- [MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation](https://mlsanity.com/paper/2412.11615/) (2024)
- [Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models](https://mlsanity.com/paper/2605.27997/) (2026)

## Abstract (arXiv)

Added toxicity in the context of translation refers to the fact of producing a translation output with more toxicity than there exists in the input. In this paper, we present MinTox which is a novel pipeline to identify added toxicity and mitigate this issue which works at inference time. MinTox uses a toxicity detection classifier which is multimodal (speech and text) and works in languages at scale. The mitigation method is applied to languages at scale and directly in text outputs. MinTox is applied to SEAMLESSM4T, which is the latest multimodal and massively multilingual machine translation system. For this system, MinTox achieves significant added toxicity mitigation across domains, modalities and language directions. MinTox manages to approximately filter out from 25% to 95% of added toxicity (depending on the modality and domain) while keeping translation quality.