{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:16:00Z","timestamp":1792782960242,"version":"4.5.0"},"reference-count":91,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"South East Technological University","id":[{"id":"https:\/\/ror.org\/03fgx6868","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources &amp; Evaluation"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Transformer-based models are the current state-of-the-art in machine translation (MT) research. These systems can generate fluent and contextually appropriate translations for many translation tasks and languages. These models are trained on large amounts of unlabelled data, often consisting of billions of examples, and naturally, this data can be imbalanced or contain stereotypes. As a result, the models may produce inaccurate gender assignments in translation and reinforce societal stereotypes. This survey investigates the nature and impact of gender bias in neural MT (NMT). It begins with an overview of how such bias emerges through different data and models. The survey then examines various evaluation frameworks proposed to systematically identify and measure gender disparities in translation outputs. It also categorises mitigation techniques based on the stage at which they operate within an NMT pipeline, from data preprocessing, model adaptation, to inference-level interventions. This survey compiles existing research and highlights challenges to facilitate the creation of more unbiased and gender-aware NMT systems.<\/jats:p>","DOI":"10.1007\/s10579-026-09931-x","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T11:42:28Z","timestamp":1784893348000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A survey of gender bias mitigation in neural machine translation"],"prefix":"10.1007","volume":"60","author":[{"given":"Neha","family":"Gajakos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Staff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brenda","family":"Murphy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John D.","family":"Kelleher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rejwanul","family":"Haque","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"key":"9931_CR3","doi-asserted-by":"crossref","unstructured":"Alves, D.M., Guerreiro, N.M., Alves, J., Pombal, J., Rei, R., de\u00a0Souza J.G.C., Colombo, P., & Martins, A.F.T. (2023). Steering large language models for machine translation with finetuning and in-context learning. In: Bouamor H, Pino J, Bali K (eds) Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics, Singapore, 11127\u201311148, https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.744, https:\/\/aclanthology.org\/2023.findings-emnlp.744\/","DOI":"10.18653\/v1\/2023.findings-emnlp.744"},{"issue":"9","key":"9931_CR4","doi-asserted-by":"publisher","first-page":"723","DOI":"10.3390\/info16090723","volume":"16","author":"D Ataman","year":"2025","unstructured":"Ataman, D., Birch, A., Habash, N., Federico, M., Koehn, P., & Cho, K. (2025). Machine translation in the era of large language models: a survey of historical and emerging problems. Information, 16(9), 723.","journal-title":"Information"},{"key":"9931_CR5","unstructured":"Ba, J.L., Kiros, J.R., & Hinton, G.E. (2016). Layer normalization. arXiv:1607.06450"},{"key":"9931_CR6","unstructured":"Bahdanau, D., Cho, K., & Bengio, Y. (2016). Neural machine translation by jointly learning to align and translate arXiv:1409.0473."},{"key":"9931_CR7","doi-asserted-by":"crossref","unstructured":"Bender, E.M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? In: Proceedings of the 2021 ACM conference on fairness, accountability, and transparency, 610\u2013623","DOI":"10.1145\/3442188.3445922"},{"key":"9931_CR8","doi-asserted-by":"crossref","unstructured":"Bentivogli, L., Savoldi, B., Negri, M., Di\u00a0Gangi, M.A., Cattoni, R., & Turchi, M. (2020). Gender in danger? evaluating speech translation technology on the MuST-SHE corpus. In: Jurafsky D, Chai J, Schluter N, Tetreault J (eds) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 6923\u20136933, https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.619, https:\/\/aclanthology.org\/2020.acl-main.619\/","DOI":"10.18653\/v1\/2020.acl-main.619"},{"key":"9931_CR9","doi-asserted-by":"crossref","unstructured":"Blodgett, S.L., Barocas, S., Daum\u00e9\u00a0III, H., & Wallach, H. (2020). Language (technology) is power: A critical survey of\" bias\" in nlp. arXiv preprint arXiv:2005.14050","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"9931_CR10","unstructured":"Bolukbasi, T., Chang, K. W., Zou, J., Saligrama, V., & Kalai, A. (2016). Man is to computer programmer as woman is to homemaker? debiasing word embeddings arXiv:1607.06520."},{"key":"9931_CR1","unstructured":"Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., \u2026 Amodei, D. (2020). Language models are few-shot learners., arXiv:2005.14165"},{"issue":"6334","key":"9931_CR11","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1126\/science.aal4230","volume":"356","author":"A Caliskan","year":"2017","unstructured":"Caliskan, A., Bryson, J. J., & Narayanan, A. (2017). Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334), 183\u2013186.","journal-title":"Science"},{"key":"9931_CR12","doi-asserted-by":"crossref","unstructured":"Choubey, P. K., Currey, A., Mathur, P., & Dinu, G. (2021). Gfst: Gender-filtered self-training for more accurate gender in translation. In Proceedings of the 2021 conference on empirical methods in natural language processing (pp. 1640\u20131654)","DOI":"10.18653\/v1\/2021.emnlp-main.123"},{"key":"9931_CR13","unstructured":"Costa-juss\u00e0, M.R., & de\u00a0Jorge, A. (2020). Fine-tuning neural machine translation on gender-balanced datasets. In Proceedings of the second workshop on gender bias in natural language processing (pp. 26\u201334)"},{"key":"9931_CR14","doi-asserted-by":"crossref","unstructured":"Currey, A., Nadejde, M., Pappagari, R.R., Mayer, M., Lauly, S., Niu, X., Hsu, B., & Dinu, G. (2022). MT-GenEval: A counterfactual and contextual dataset for evaluating gender accuracy in machine translation. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 4287\u20134299, https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.288, https:\/\/aclanthology.org\/2022.emnlp-main.288\/","DOI":"10.18653\/v1\/2022.emnlp-main.288"},{"key":"9931_CR15","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, pp 4171\u20134186, https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423\/","DOI":"10.18653\/v1\/N19-1423"},{"key":"9931_CR16","doi-asserted-by":"crossref","unstructured":"Di\u00a0Gangi, M.A., Cattoni, R., Bentivogli, L., Negri, M., & Turchi, M. (2019). MuST-C: a Multilingual Speech Translation Corpus. In: Burstein J, Doran C, Solorio T (eds) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 2012\u20132017, https:\/\/doi.org\/10.18653\/v1\/N19-1202, https:\/\/aclanthology.org\/N19-1202\/","DOI":"10.18653\/v1\/N19-1202"},{"key":"9931_CR17","doi-asserted-by":"crossref","unstructured":"Dodge, J., Sap, M., Marasovi\u0107, A., Agnew, W., Ilharco, G., Groeneveld, D., Mitchell, M., & Gardner, M. (2021). Documenting large webtext corpora: A case study on the colossal clean crawled corpus arXiv:2104.08758.","DOI":"10.18653\/v1\/2021.emnlp-main.98"},{"key":"9931_CR18","unstructured":"Fan, A., Bhosale, S., Schwenk, H., Ma, Z., El-Kishky, A., Goyal, S., Baines, M., Celebi, O., Wenzek, G., Chaudhary, V., Goyal, N., Birch, T., Liptchinsky, V., Edunov, S., Grave, E., Auli, M., & Joulin, A. (2020). Beyond english-centric multilingual machine translation., arXiv:2010.11125"},{"key":"9931_CR19","unstructured":"Fleisig, E., & Fellbaum, C. (2022). Mitigating gender bias in machine translation through adversarial learning, arXiv preprint. arXiv:2203.10675"},{"key":"9931_CR20","doi-asserted-by":"crossref","unstructured":"Fraser, K. C., Nejadgholi, I., & Kiritchenko, S. (2021). Understanding and countering stereotypes: A computational approach to the stereotype content model arXiv:2106.02596.","DOI":"10.18653\/v1\/2021.acl-long.50"},{"issue":"3","key":"9931_CR21","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1145\/230538.230561","volume":"14","author":"B Friedman","year":"1996","unstructured":"Friedman, B., & Nissenbaum, H. (1996). Bias in computer systems. ACM Transactions on information systems (TOIS), 14(3), 330\u2013347.","journal-title":"ACM Transactions on information systems (TOIS)"},{"key":"9931_CR22","doi-asserted-by":"crossref","unstructured":"Gain, B., Bandyopadhyay, D., & Ekbal, A. (2025). Bridging the linguistic divide: A survey on leveraging large language models for machine translation arXiv:2504.01919.","DOI":"10.1007\/s10579-026-09919-7"},{"key":"9931_CR23","doi-asserted-by":"crossref","unstructured":"Gao, Y., Herold, C., Yang, Z., & Ney, H. (2022). Is encoder-decoder redundant for neural machine translation? In: He Y, Ji H, Li S, Liu Y, Chang CH (eds) Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Online only, pp 562\u2013574, https:\/\/doi.org\/10.18653\/v1\/2022.aacl-main.43, https:\/\/aclanthology.org\/2022.aacl-main.43\/","DOI":"10.18653\/v1\/2022.aacl-main.43"},{"key":"9931_CR24","doi-asserted-by":"crossref","unstructured":"Gete, H., & Etchegoyhen, T. (2024a). Does context help mitigate gender bias in neural machine translation? In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds) Findings of the Association for Computational Linguistics: EMNLP 2024. Association for Computational Linguistics, Miami, Florida, USA, pp 14788\u201314794, https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.868, https:\/\/aclanthology.org\/2024.findings-emnlp.868\/","DOI":"10.18653\/v1\/2024.findings-emnlp.868"},{"key":"9931_CR25","unstructured":"Gete, H., & Etchegoyhen, T. (2024b). Promoting target data in context-aware neural machine translation. arXiv preprint arXiv:2402.06342"},{"key":"9931_CR26","unstructured":"Gkovedarou, E., Daems, J., & Bruyne, L. D. (2025). Gender bias in english-to-greek machine translation arXiv:2506.09558."},{"key":"9931_CR27","doi-asserted-by":"crossref","unstructured":"Hansal, O., Le, N.T., & Sadat, F. (2022). Indigenous language revitalization and the dilemma of gender bias. In: Hardmeier, C., Basta, C., Costa-juss\u00e0, M.R., Stanovsky, G., Gonen, H. (eds) Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP). Association for Computational Linguistics, Seattle, Washington, pp 244\u2013254, https:\/\/doi.org\/10.18653\/v1\/2022.gebnlp-1.25, https:\/\/aclanthology.org\/2022.gebnlp-1.25\/","DOI":"10.18653\/v1\/2022.gebnlp-1.25"},{"key":"9931_CR28","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770\u2013778, https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"9931_CR29","unstructured":"IMD IIfMD (2025). Understanding gender bias: Key issues and strategies for change 2024. https:\/\/www.imd.org\/blog\/management\/gender-bias\/, accessed on 14 June 2025"},{"key":"9931_CR30","doi-asserted-by":"crossref","unstructured":"Junczys-Dowmunt, M., Grundkiewicz, R., Dwojak, T., Hoang, H., Heafield, K., Neckermann, T., Seide, F., Germann, U., Aji, A.F., Bogoychev, N., Martins, A.F.T., & Birch, A. (2018). Marian: Fast neural machine translation in c++. , arXiv:1804.00344","DOI":"10.18653\/v1\/P18-4020"},{"key":"9931_CR31","doi-asserted-by":"crossref","unstructured":"Kalchbrenner, N., & Blunsom, P. (2013). Recurrent continuous translation models. In: Yarowsky D, Baldwin T, Korhonen A, Livescu K, Bethard S (eds) Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Seattle, Washington, USA, 1700\u20131709, https:\/\/aclanthology.org\/D13-1176\/","DOI":"10.18653\/v1\/D13-1176"},{"issue":"2","key":"9931_CR32","first-page":"111","volume":"3","author":"E Kocakaya","year":"2025","unstructured":"Kocakaya, E. (2025). Equivalence, translator subjectivity, and rewriting in the context of feminist translation theory. Abant \u00c7eviribilim Dergisi, 3(2), 111\u2013123.","journal-title":"Abant \u00c7eviribilim Dergisi"},{"key":"9931_CR33","unstructured":"Kumar, C. V., Urlana, A., Kanumolu, G., Garlapati, B. M., & Mishra, P. (2025). No llm is free from bias: A comprehensive study of bias evaluation in large language models arXiv:2503.11985."},{"key":"9931_CR34","doi-asserted-by":"crossref","unstructured":"Lee, M., Koh, H., Lee, K., Zhang, D., Kim, M., & Jung, K. (2023). Target-agnostic gender-aware contrastive learning for mitigating bias in multilingual machine translation. arXiv preprint arXiv:2305.14016","DOI":"10.18653\/v1\/2023.emnlp-main.1046"},{"key":"9931_CR35","doi-asserted-by":"crossref","unstructured":"Levy, S., Lazar, K., & Stanovsky, G. (2021). Collecting a large-scale gender bias dataset for coreference resolution and machine translation. In: Moens, M.F., Huang, X., Specia, L., Yih SWt (eds) Findings of the Association for Computational Linguistics: EMNLP 2021. Association for Computational Linguistics, Punta Cana, Dominican Republic, pp 2470\u20132480, https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.211, https:\/\/aclanthology.org\/2021.findings-emnlp.211\/","DOI":"10.18653\/v1\/2021.findings-emnlp.211"},{"key":"9931_CR36","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020). BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Jurafsky D, Chai J, Schluter N, Tetreault J (eds) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 7871\u20137880, https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703, https:\/\/aclanthology.org\/2020.acl-main.703\/","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"9931_CR38","doi-asserted-by":"crossref","unstructured":"Lu, K., Mardziel, P., Wu, F., Amancharla, P., & Datta, A. (2019). Gender bias in neural natural language processing arXiv:1807.11714.","DOI":"10.1007\/978-3-030-62077-6_14"},{"key":"9931_CR37","unstructured":"Lu, T., Aepli, N., & Rios, A. (2023). Reducing gender bias in NMT with FUDGE. In: Vanmassenhove, E., Savoldi, B., Bentivogli, L., Daems, J., Hackenbuchner, J. (eds) Proceedings of the First Workshop on Gender-Inclusive Translation Technologies. European Association for Machine Translation, Tampere, Finland, pp 61\u201369, https:\/\/aclanthology.org\/2023.gitt-1.6\/"},{"key":"9931_CR39","unstructured":"Manna, C., Alishahi, A., Blain, F., & Vanmassenhove, E. (2025). Are we paying attention to her? investigating gender disambiguation and attention in machine translation arXiv:2505.08546."},{"key":"9931_CR40","unstructured":"Maudslay, R. H., Gonen, H., Cotterell, R., & Teufel, S. (2019). It\u2019s all in the name: mitigating gender bias with name-based counterfactual data substitution arXiv:1909.00871 arXiv preprint."},{"key":"9931_CR41","unstructured":"Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space arXiv:1301.3781."},{"key":"9931_CR42","doi-asserted-by":"crossref","unstructured":"Mohammadshahi, A., Nikoulina, V., Berard, A., Brun, C., Henderson, J., & Besacier, L. (2022). SMaLL-100: Introducing shallow multilingual machine translation model for low-resource languages. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, pp 8348\u20138359, https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.571, https:\/\/aclanthology.org\/2022.emnlp-main.571\/","DOI":"10.18653\/v1\/2022.emnlp-main.571"},{"key":"9931_CR43","unstructured":"Naik, R., Rarrick, S., & Chowdhary, V. (2023). Reducing gender bias in machine translation through counterfactual data generation arXiv:2311.16362."},{"key":"9931_CR44","doi-asserted-by":"crossref","unstructured":"Ott, M., Edunov, S., Baevski, A., Fan, A., Gross, S., Ng, N., Grangier, D., & Auli, M. (2019). fairseq: A fast, extensible toolkit for sequence modeling. In: Ammar W, Louis A, Mostafazadeh N (eds) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). Association for Computational Linguistics, Minneapolis, Minnesota, 48\u201353, https:\/\/doi.org\/10.18653\/v1\/N19-4009, https:\/\/aclanthology.org\/N19-4009\/","DOI":"10.18653\/v1\/N19-4009"},{"key":"9931_CR45","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, W.J. (2002). Bleu: a method for automatic evaluation of machine translation. In: Isabelle P, Charniak E, Lin D (eds) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, 311\u2013318, https:\/\/doi.org\/10.3115\/1073083.1073135, https:\/\/aclanthology.org\/P02-1040","DOI":"10.3115\/1073083.1073135"},{"key":"9931_CR46","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C. (2014). GloVe: Global vectors for word representation. In: Moschitti A, Pang B, Daelemans W (eds) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Doha, Qatar, pp 1532\u20131543, https:\/\/doi.org\/10.3115\/v1\/D14-1162, https:\/\/aclanthology.org\/D14-1162\/","DOI":"10.3115\/v1\/D14-1162"},{"key":"9931_CR47","unstructured":"Piergentili, A., Savoldi, B., Negri, M., & Bentivogli, L. (2024). Enhancing gender-inclusive machine translation with neomorphemes and large language models arXiv:2405.08477 arXiv preprint."},{"key":"9931_CR48","doi-asserted-by":"crossref","unstructured":"Popovi\u0107, M. (2015). chrF: character n-gram F-score for automatic MT evaluation. In: Bojar, O., Chatterjee, R., Federmann, C., Haddow, B., Hokamp, C., Huck, M., Logacheva, V., Pecina, P. (eds) Proceedings of the Tenth Workshop on Statistical Machine Translation. Association for Computational Linguistics, Lisbon, Portugal, pp 392\u2013395, https:\/\/doi.org\/10.18653\/v1\/W15-3049, https:\/\/aclanthology.org\/W15-3049\/","DOI":"10.18653\/v1\/W15-3049"},{"key":"9931_CR49","doi-asserted-by":"publisher","first-page":"6363","DOI":"10.1007\/s00521-019-04144-6","volume":"32","author":"MO Prates","year":"2020","unstructured":"Prates, M. O., Avelar, P. H., & Lamb, L. C. (2020). Assessing gender bias in machine translation: a case study with google translate. Neural Computing and Applications, 32, 6363\u20136381.","journal-title":"Neural Computing and Applications"},{"key":"9931_CR50","doi-asserted-by":"crossref","unstructured":"Qu, Z., Wang, Y., Ding, C., Tanaka, H., Utiyama, M., Watanabe, T. (2025). Improving language transfer capability of decoder-only architecture in multilingual neural machine translation. In: Adelani, D.I., Arnett, C., Ataman, D., Chang, T.A., Gonen, H., Raja, R., Schmidt, F., Stap, D., Wang, J. (eds) Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025). Association for Computational Linguistics, Suzhuo, China, pp 178\u2013195, https:\/\/doi.org\/10.18653\/v1\/2025.mrl-main.13, https:\/\/aclanthology.org\/2025.mrl-main.13\/","DOI":"10.18653\/v1\/2025.mrl-main.13"},{"issue":"8","key":"9931_CR51","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9.","journal-title":"OpenAI blog"},{"issue":"140","key":"9931_CR52","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140), 1\u201367. http:\/\/jmlr.org\/papers\/v21\/20-074.html.","journal-title":"Journal of Machine Learning Research"},{"key":"9931_CR54","doi-asserted-by":"crossref","unstructured":"Rarrick, S., Naik, R., Poudel, S., & Chowdhary, V. (2024). GATE X-E : A challenge set for gender-fair translations from weakly-gendered languages. In: Ku, L.W., Martins, A., Srikumar, V. (eds) Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics, Bangkok, Thailand, pp 8526\u20138546, https:\/\/doi.org\/10.18653\/v1\/2024.findings-acl.504, https:\/\/aclanthology.org\/2024.findings-acl.504\/","DOI":"10.18653\/v1\/2024.findings-acl.504"},{"key":"9931_CR55","doi-asserted-by":"crossref","unstructured":"Rei, R., Stewart, C., Farinha, A. C., & Lavie, A. (2020). Comet: A neural framework for mt evaluation arXiv:2009.09025.","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"9931_CR56","doi-asserted-by":"crossref","unstructured":"Rudinger, R., Naradowsky, J., Leonard, B., & Van Durme, B. (2018). Gender bias in coreference resolution arXiv:1804.09301 arXiv preprint.","DOI":"10.18653\/v1\/N18-2002"},{"key":"9931_CR57","doi-asserted-by":"crossref","unstructured":"Sant, A., Escolano, C., Mash, A., Fornaciari, F., & Melero, M. (2024). The power of prompts: Evaluating and mitigating gender bias in mt with llms arXiv:2407.18786 arXiv preprint.","DOI":"10.18653\/v1\/2024.gebnlp-1.7"},{"key":"9931_CR58","unstructured":"Saunders, D., Sallis, R., & Byrne, B. (2020). Neural machine translation doesn\u2019t translate gender coreference right unless you make it arXiv:2010.05332 arXiv preprint."},{"key":"9931_CR59","doi-asserted-by":"crossref","unstructured":"Saunders, D., Sallis, R., & Byrne, B. (2021). First the worst: Finding better gender translations during beam search arXiv:2104.07429 arXiv preprint.","DOI":"10.18653\/v1\/2022.findings-acl.301"},{"key":"9931_CR60","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1162\/tacl_a_00401","volume":"9","author":"B Savoldi","year":"2021","unstructured":"Savoldi, B., Gaido, M., Bentivogli, L., Negri, M., & Turchi, M. (2021). Gender bias in machine translation. Transactions of the Association for Computational Linguistics, 9, 845\u2013874.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"9931_CR61","doi-asserted-by":"crossref","unstructured":"Sennrich, R., & Haddow, B. (2016). Linguistic input features improve neural machine translation arXiv:1606.02892 arXiv preprint.","DOI":"10.18653\/v1\/W16-2209"},{"key":"9931_CR62","doi-asserted-by":"crossref","unstructured":"Sharma, S., Dey, M., & Sinha, K. (2022). How sensitive are translation systems to extra contexts? mitigating gender bias in neural machine translation models through relevant contexts arXiv:2205.10762.","DOI":"10.18653\/v1\/2022.findings-emnlp.143"},{"key":"9931_CR63","unstructured":"Snover, M., Dorr, B., Schwartz, R., Micciulla, L., & Makhoul, J. (2006). A study of translation edit rate with targeted human annotation. In: Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers. Association for Machine Translation in the Americas, Cambridge, Massachusetts, USA, pp 223\u2013231, https:\/\/aclanthology.org\/2006.amta-papers.25\/"},{"key":"9931_CR64","doi-asserted-by":"crossref","unstructured":"Stafanovi\u010ds, A., Bergmanis, T., & Pinnis, M. (2020). Mitigating gender bias in machine translation with target gender annotations arXiv:2010.06203 arXiv preprint.","DOI":"10.18653\/v1\/2020.wmt-1.73"},{"key":"9931_CR65","doi-asserted-by":"crossref","unstructured":"Stanovsky, G., Smith, N. A., & Zettlemoyer, L. (2019). Evaluating gender bias in machine translation arXiv:1906.00591 arXiv preprint.","DOI":"10.18653\/v1\/P19-1164"},{"key":"9931_CR66","unstructured":"Team, N., Costa-juss\u00e0, M.R., Cross, J., \u00c7elebi, O., Elbayad, M., Heafield, K., Heffernan, K., Kalbassi, E., Lam, J., Licht, D., Maillard, J., Sun, A., Wang, S., Wenzek, G., Youngblood, A., Akula, B., Barrault, L., Gonzalez, G.M., Hansanti, P., Hoffman, J., Jarrett, S., Sadagopan, K.R., Rowe, D., Spruit, S., Tran, C., Andrews, P., Ayan, N.F., Bhosale, S., Edunov, S., Fan, A., Gao, C., Goswami, V., Guzm\u00e1n, F., Koehn, P., Mourachko, A., Ropers, C., Saleem, S., Schwenk, H., & Wang, J. (2022). No language left behind: Scaling human-centered machine translation. arXiv:2207.04672"},{"key":"9931_CR67","unstructured":"Tiedemann, J., & Thottingal, S. (2020). OPUS-MT \u2013 building open translation services for the world. In: Martins, A., Moniz, H., Fumega, S., Martins, B., Batista, F., Coheur, L., Parra, C., Trancoso, I., Turchi, M., Bisazza, A., Moorkens, J., Guerberof, A., Nurminen, M., Marg, L., Forcada, M.L. (eds) Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. European Association for Machine Translation, Lisboa, Portugal, 479\u2013480, https:\/\/aclanthology.org\/2020.eamt-1.61\/"},{"key":"9931_CR68","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., & Lample, G. (2023a). Llama: Open and efficient foundation language models. arXiv:2302.13971"},{"key":"9931_CR2","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., Bikel, D., Blecher, L., Ferrer, C. C., Chen, M., Cucurull, G., Esiobu, D., Fernandes, J., Fu, J., Fu, W., & Scialom, T. (2023b). Llama 2: Open foundation and fine-tuned chat models."},{"key":"9931_CR69","unstructured":"Traag, V. A., & Waltman, L. (2024). Causal foundations of bias, disparity and fairness arXiv:2207.13665."},{"key":"9931_CR70","unstructured":"UN\u00a0Women H. (2024). Facts and figures: Economic empowerment. https:\/\/www.unwomen.org\/en\/what-we-do\/economic-empowerment\/facts-and-figures#_edn18, last updated February 2024"},{"key":"9931_CR71","unstructured":"UNDP UNDP. (2023). 2023 gender social norms index (gsni). UNDP (United Nations Development Programme)"},{"key":"9931_CR72","doi-asserted-by":"crossref","unstructured":"Vamvas, J., & Sennrich, R. (2021). Contrastive conditioning for assessing disambiguation in MT: A case study of distilled bias. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t (eds) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, pp 10246\u201310265, https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.803, https:\/\/aclanthology.org\/2021.emnlp-main.803\/","DOI":"10.18653\/v1\/2021.emnlp-main.803"},{"key":"9931_CR73","doi-asserted-by":"crossref","unstructured":"Vashishtha, A., Ahuja, K., & Sitaram, S. (2023). On evaluating and mitigating gender biases in multilingual settings arXiv:2307.01503.","DOI":"10.18653\/v1\/2023.findings-acl.21"},{"key":"9931_CR74","unstructured":"Vaswani, A., Bengio, S., Brevdo, E., Chollet, F., Gomez, A., Gouws, S., Jones, L., Kaiser, \u0141., Kalchbrenner, N., Parmar, N., Sepassi, R., Shazeer, N., & Uszkoreit, J. (2018). Tensor2Tensor for neural machine translation. In: Cherry C, Neubig G (eds) Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track). Association for Machine Translation in the Americas, Boston, MA, pp 193\u2013199, https:\/\/aclanthology.org\/W18-1819\/"},{"key":"9931_CR75","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems 30"},{"key":"9931_CR76","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2023). Attention is all you need arXiv:1706.03762."},{"key":"9931_CR77","unstructured":"Webster, K., Wang, X., Tenney, I., Beutel, A., Pitler, E., Pavlick, E., Chen, J., Petrov, C. E., & S. (2020). Measuring and reducing gendered correlations in pre-trained models arXiv:2010.06032 arXiv preprint."},{"key":"9931_CR78","doi-asserted-by":"crossref","unstructured":"Winter, H., & Hoffman, D. A. (2022). Follow the science: Proven strategies for reducing unconscious bias (pp. 1\u201363). Pepperdine University Legal Studies. Research Paper (2024\/14).","DOI":"10.2139\/ssrn.4864197"},{"key":"9931_CR79","unstructured":"Wong, A. (2020). Mitigating gender bias in neural machine translation using counterfactual data. CUNY Academic Works."},{"key":"9931_CR80","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1162\/tacl_a_00461","volume":"10","author":"L Xue","year":"2022","unstructured":"Xue, L., Barua, A., Constant, N., Al-Rfou, R., Narang, S., Kale, M., Roberts, A., & Raffel, C. (2022). ByT5: Towards a token-free future with pre-trained byte-to-byte models. Transactions of the Association for Computational Linguistics, 10, 291\u2013306. https:\/\/doi.org\/10.1162\/tacl_a_00461https:\/\/aclanthology.org\/2022.tacl-1.17\/.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"9931_CR81","doi-asserted-by":"crossref","unstructured":"Xue L, Constant, N., Roberts, A., Kale, M., Al-Rfou, R., Siddhant, A., Barua, A., & Raffel, C. (2021). mT5: A massively multilingual pre-trained text-to-text transformer. In: Toutanova, K., Rumshisky, A., Zettlemoyer, L., Hakkani-Tur, D., Beltagy, I., Bethard, S., Cotterell, R., Chakraborty, T., Zhou, Y. (eds) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, pp 483\u2013498, https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.41, https:\/\/aclanthology.org\/2021.naacl-main.41\/","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"9931_CR82","doi-asserted-by":"publisher","unstructured":"Yang, K., & Klein, D. (2021). Fudge: Controlled text generation with future discriminators. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.276, http:\/\/dx.doi.org\/10.18653\/v1\/2021.naacl-main.276","DOI":"10.18653\/v1\/2021.naacl-main.276"},{"key":"9931_CR83","unstructured":"Yang, S., Wang, Y., & Chu, X. (2020). A survey of deep learning techniques for neural machine translation arXiv:2002.07526."},{"key":"9931_CR84","doi-asserted-by":"crossref","unstructured":"Zahraei, P. S., & Emami, A. (2025). Translate with care: Addressing gender bias, neutrality, and reasoning in large language model translations arXiv:2506.00748 arXiv preprint.","DOI":"10.18653\/v1\/2025.findings-acl.26"},{"key":"9931_CR85","unstructured":"Zhang, B., Moiseev, F., Suganthan, A. J., Ma, P., Bhupatiraju, M., Lebron, S., Firat, F., Joulin, O., Dong, A., & Z. (2025). Encoder-decoder gemma: Improving the quality-efficiency trade-off via adaptation arXiv:2504.06225."},{"issue":"5","key":"9931_CR86","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MIS.2015.69","volume":"30","author":"J Zhang","year":"2015","unstructured":"Zhang, J., Zong, C., et al. (2015). Deep neural networks in machine translation: An overview. IEEE Intelligent Systems, 30(5), 16\u201325.","journal-title":"IEEE Intelligent Systems"},{"key":"9931_CR87","doi-asserted-by":"crossref","unstructured":"Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K. W. (2018). Gender bias in coreference resolution: Evaluation and debiasing methods arXiv:1804.06876 arXiv preprint.","DOI":"10.18653\/v1\/N18-2003"},{"key":"9931_CR88","first-page":"227","volume":"2024","author":"A Zhou","year":"2024","unstructured":"Zhou, A., & Wilson, C. (2024). Modeling morphosyntactic agreement as neural search: a case study of hindi-urdu. Proceedings of the Society for Computation in Linguistics, 2024, 227\u2013239.","journal-title":"Proceedings of the Society for Computation in Linguistics"},{"key":"9931_CR89","doi-asserted-by":"crossref","unstructured":"Zhu, D., Chen, P., Zhang, M., Haddow, B., Shen, X., & Klakow, D. (2024). Fine-tuning large language models to translate: Will a touch of noisy data in misaligned languages suffice? Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (pp. 388\u2013409)","DOI":"10.18653\/v1\/2024.emnlp-main.24"},{"key":"9931_CR90","doi-asserted-by":"crossref","unstructured":"Zhu, S., & Rzeszotarski, J. M. (2025). What we talk about when we talk about lms: Implicit paradigm shifts and the ship of language models arXiv:2407.01929.","DOI":"10.18653\/v1\/2025.naacl-long.237"},{"key":"9931_CR91","doi-asserted-by":"crossref","unstructured":"Zmigrod, R., Mielke, S.J., Wallach, H., & Cotterell, R. (2019). Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, pp 1651\u20131661, https:\/\/doi.org\/10.18653\/v1\/P19-1161, https:\/\/aclanthology.org\/P19-1161\/","DOI":"10.18653\/v1\/P19-1161"},{"key":"9931_CR92","doi-asserted-by":"crossref","unstructured":"Zouhar, V., Kocmi, T., & Sachan, M. (2025). AI-assisted human evaluation of machine translation. In: Chiruzzo L, Ritter A, Wang L (eds) Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Association for Computational Linguistics, Albuquerque, New Mexico, pp 4936\u20134950, https:\/\/doi.org\/10.18653\/v1\/2025.naacl-long.255, https:\/\/aclanthology.org\/2025.naacl-long.255\/","DOI":"10.18653\/v1\/2025.naacl-long.255"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-026-09931-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-026-09931-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-026-09931-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T02:08:31Z","timestamp":1791252511000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-026-09931-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,24]]},"references-count":91,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["9931"],"URL":"https:\/\/doi.org\/10.1007\/s10579-026-09931-x","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,24]]},"assertion":[{"value":"25 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"60"}}