mlsanityData to 7 Oct 2026

What Triggers my Model? Contrastive Explanations Inform Gender Choices by Translation Models

arXiv 2512.08440 ↗First posted 9 Dec 2025cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs). Yet, research in this area has been limited in relation to a manifested problem in these models: gender bias. In this work, we aim to move away from simply measuring bias to exploring its origins. Working with gender-ambiguous natural source data, this exploratory study examines which context, in the form of input tokens in the source sentence (EN), influences (or triggers) the NMT model's choice of a certain gender inflection in the target languages (DE/ES). To analyse this, we compute saliency attribution based on contrastive translations. We first address the challenge of the lack of a scoring threshold and specifically examine different attribution levels of source words on the model's gender decisions in the translation. We compare salient source words with human perceptions of gender and demonstrate a noticeable overlap between human perceptions and model attribution. Additionally, we provide a linguistic analysis of salient words. Our work showcases the relevance of understanding model translation decisions in terms of gender, how this compares to human decisions and that this information should be leveraged to mitigate gender bias.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 61 references that are in the map. First posted on arXiv 9 Dec 2025.

Builds on

35 of 61 references.

References · 35

  1. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  2. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  3. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  4. 2019Evaluating Gender Bias in Machine Translationcited by 247
  5. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  6. 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 165
  7. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 155
  8. 2020The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?cited by 122
  9. 2018Context-Aware Neural Machine Translation Learns Anaphora Resolutioncited by 97
  10. 2019Evaluating the Underlying Gender Bias in Contextualized Word Embeddingscited by 94
  11. 2022Interpreting Language Models with Contrastive Explanationscited by 91
  12. 2020Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problemcited by 86
23 more
  1. 2023Inseq: An Interpretability Toolkit for Sequence Generation Modelscited by 78
  2. 2019An Evaluation of the Human-Interpretability of Explanationcited by 71
  3. 2021"Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classificationcited by 66
  4. 2021Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translationcited by 62
  5. 2019On Measuring Gender Bias in Translation of Gender-neutral Pronounscited by 59
  6. 2020Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpuscited by 57
  7. 2021NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternativescited by 46
  8. 2016How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairscited by 39
  9. 2023Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scalecited by 23
  10. 2023Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challengescited by 22
  11. 2020Gender Coreference and Bias Evaluation at WMT 2020cited by 21
  12. 2021Do Context-Aware Translation Models Pay the Right Attention?cited by 21
  13. 2023A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translationcited by 19
  14. 2021GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomenacited by 16
  15. 2023Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Modelcited by 14
  16. 2024A Prompt Response to the Demand for Automatic Gender-Neutral Translationcited by 12
  17. 2025Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTEcited by 12
  18. 2023Gender, names and other mysteries: Towards the ambiguous for gender-inclusive translationcited by 7
  19. 2025Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translationcited by 7
  20. 2025Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translationcited by 5
  21. 2024Gender Bias in Machine Translation and The Era of Large Language Modelscited by 4
  22. 2025Gender Bias in English-to-Greek Machine Translationcited by 3
  23. 2025The Unheard Alternative: Contrastive Explanations for Speech-to-Text Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Modelscited by 2
  2. 2026Explaining GAND: A Resource on Gender-Ambiguous Natural Data & Contrastive Attributioncited by 0