mlsanityData to 7 Oct 2026

First the worst: Finding better gender translations during beam search

arXiv 2104.07429 ↗First posted 15 Apr 2021cs.CLcited by 28

Not on the map. Why?

Abstract (arXiv)

Neural machine translation inference procedures like beam search generate the most likely output under the model. This can exacerbate any demographic biases exhibited by the model. We focus on gender bias resulting from systematic errors in grammatical gender translation, which can lead to human referents being misrepresented or misgendered. Most approaches to this problem adjust the training data or the model. By contrast, we experiment with simply adjusting the inference procedure. We experiment with reranking nbest lists using gender features obtained automatically from the source sentence, and applying gender constraints while decoding to improve nbest list gender diversity. We find that a combination of these techniques allows large gains in WinoMT accuracy without requiring additional bilingual data or an additional NMT model.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 26 of its 54 references that are in the map. First posted on arXiv 15 Apr 2021.

Builds on

26 of 54 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  6. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  7. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  8. 2018Gender Bias in Coreference Resolutioncited by 438
  9. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  10. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  11. 2019Evaluating Gender Bias in Machine Translationcited by 247
  12. 2019Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overviewcited by 137
14 more
  1. 2019On NMT Search Errors and Model Errors: Cat Got Your Tongue?cited by 114
  2. 2019Getting Gender Right in Neural Machine Translationcited by 98
  3. 2020Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problemcited by 86
  4. 2018Tensor2Tensor for Neural Machine Translationcited by 85
  5. 2019Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniquescited by 65
  6. 2019Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translationcited by 45
  7. 2021They, Them, Theirs: Rewriting with Gender-Neutral Englishcited by 44
  8. 2020Mitigating Gender Bias in Machine Translation with Target Gender Annotationscited by 42
  9. 2020Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make Itcited by 40
  10. 2019Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injectioncited by 27
  11. 2020Decoding and Diversity in Machine Translationcited by 15
  12. 2016Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directionscited by 7
  13. 2018DEMorphy, German Language Morphological Analyzercited by 4
  14. 2016Syntactically Guided Neural Machine Translationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 9; 2024: 7; 2025: 4; 2026: 4.

28 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  2. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  3. 2024Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypescited by 58
  4. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  5. 2025FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steeringcited by 37
  6. 2022Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimizationcited by 32
  7. 2022On Learning Fairness and Accuracy on Multiple Subgroupscited by 31
  8. 2024SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agentscited by 30
  9. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  10. 2023Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challengescited by 22
  11. 2023Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with the GeNTE Corpuscited by 20
  12. 2024What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Studycited by 15
16 more
  1. 2023Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Modelcited by 14
  2. 2021The Arabic Parallel Gender Corpus 2.0: Extensions and Analysescited by 12
  3. 2023Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societiescited by 11
  4. 2024Potential and Challenges of Model Editing for Social Debiasingcited by 10
  5. 2023Gender, names and other mysteries: Towards the ambiguous for gender-inclusive translationcited by 7
  6. 2023Test Suites Task: Evaluation of Gender Fairness in MT with MuST-SHE and INEScited by 6
  7. 2025BiasFilter: An Inference-Time Debiasing Framework for Large Language Modelscited by 6
  8. 2025Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translationcited by 5
  9. 2023A Group Fairness Lens for Large Language Modelscited by 4
  10. 2024Generating Gender Alternatives in Machine Translationcited by 3
  11. 2023Reducing Gender Bias in Machine Translation through Counterfactual Data Generationcited by 1
  12. 2025Integrating gender inclusivity into large language models via instruction tuningcited by 0
  13. 2026Cultural Fidelity in English-to-Hindi Translation: A Preservation-Fluency Frontier for Gender Recoverabilitycited by 0
  14. 2026When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigationcited by 0
  15. 2026Explaining GAND: A Resource on Gender-Ambiguous Natural Data & Contrastive Attributioncited by 0
  16. 2026Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Rerankingcited by 0