mlsanityData to 14 Oct 2026

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

arXiv 2311.06532 ↗First posted 11 Nov 2023cs.CLcited by 5

Not on the map. Why?

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.

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

10 of 18 references.

References · 10

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  3. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  4. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
  5. 2022"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Datasetcited by 162
  6. 2022Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformercited by 45
  7. 2022Toxicity in Multilingual Machine Translation at Scalecited by 26
  8. 2022BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metriccited by 16
  9. 2021DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterancescited by 14
  10. 2023ReSeTOX: Re-learning attention weights for toxicity mitigation in machine translationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024From One to Many: Expanding the Scope of Toxicity Mitigation in Language Modelscited by 18
  2. 2025Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxificationcited by 3
  3. 2024Towards Massive Multilingual Holistic Biascited by 0
  4. 2024MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluationcited by 0
  5. 2026Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Modelscited by 0