mlsanityData to 14 Oct 2026

ReSeTOX: Re-learning attention weights for toxicity mitigation in machine translation

arXiv 2305.11761 ↗First posted 19 May 2023cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Our proposed method, ReSeTOX (REdo SEarch if TOXic), addresses the issue of Neural Machine Translation (NMT) generating translation outputs that contain toxic words not present in the input. The objective is to mitigate the introduction of toxic language without the need for re-training. In the case of identified added toxicity during the inference process, ReSeTOX dynamically adjusts the key-value self-attention weights and re-evaluates the beam search hypotheses. Experimental results demonstrate that ReSeTOX achieves a remarkable 57% reduction in added toxicity while maintaining an average translation quality of 99.5% across 164 languages.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 16 of its 22 references that are in the map. First posted on arXiv 19 May 2023.

Builds on

16 of 22 references.

References · 16

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  3. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  4. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  5. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 356
  6. 2021The GEM Benchmark: Natural Language Generation, its Evaluation and Metricscited by 239
  7. 2021Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasetscited by 181
  8. 2020Recipes for Safety in Open-domain Chatbotscited by 170
  9. 2022"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Datasetcited by 162
  10. 2021ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmeticcited by 150
  11. 2022Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Bettercited by 75
  12. 2021Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translationcited by 65
4 more
  1. 2022Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformercited by 45
  2. 2022Toxicity in Multilingual Machine Translation at Scalecited by 26
  3. 2022Zero-Shot Video Captioning with Evolving Pseudo-Tokenscited by 25
  4. 2022Reward Modeling for Mitigating Toxicity in Transformer-based Language Modelscited by 18

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2023Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translationcited by 5
  2. 2025Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigationcited by 3
  3. 2024MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluationcited by 0