{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T10:16:43Z","timestamp":1775125003490,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:00:00Z","timestamp":1775088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Gender bias embedded in legal and professional texts perpetuates systemic inequality, yet research on bias identification and mitigation remains largely confined to English. Morphologically rich languages such as Greek, where grammatical gender pervades nouns, adjectives, pronouns, and participles, present unique challenges that existing approaches fail to address. This paper elaborates on a systematic methodology primarily focusing on identifying and mitigating gender bias in Greek-language job advertisements and legal documents. To accomplish that task, we define a taxonomy of nine gender bias rules tailored to the linguistic properties of Greek and construct domain-specific annotated datasets comprising 90 expert-curated few-shot examples across both textual domains. Using these resources, we employ XML-structured prompt engineering with in-context learning (ICL)and systematically compare three classes of models: (i) commercial large language models (LLMs), namely Claude Sonnet 4.5 and GPT-5.2, (ii) two open-weight small language models (SLMs), Mistral Small (24B) and Ministral (14B), and (iii) Llama Krikri (8B), a Greek-native language model built on Llama 3.1 and fine-tuned on high-quality Greek corpora. For each input text, the system identifies biased expressions, maps them to specific bias rules, provides explanations, and generates a fully corrected inclusive version. Our experiments reveal substantial performance disparities across model scales and linguistic specialization, with LLMs demonstrating superior contextual reasoning and SLMs exhibiting systematic over-correction and grammatical errors in Greek morphology. We further introduce a critical meta-rule addressing gender agreement with named entities to prevent spurious corrections in legal texts referencing identified individuals. The findings highlight the importance of model scale, language-specific adaptation, and carefully designed prompting strategies for bias mitigation in underrepresented languages.<\/jats:p>","DOI":"10.3390\/info17040342","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T09:26:12Z","timestamp":1775121972000},"page":"342","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unbiasing Greek: In-Context Learning Strategies for Gender Bias Identification and Mitigation for Legal Documents and Job Ads"],"prefix":"10.3390","volume":"17","author":[{"given":"Dimitrios","family":"Doumanas","sequence":"first","affiliation":[{"name":"Intelligent Systems Lab, Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9769-5583","authenticated-orcid":false,"given":"Andreas","family":"Soularidis","sequence":"additional","affiliation":[{"name":"Intelligent Systems Lab, Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaos","family":"Zafeiropoulos","sequence":"additional","affiliation":[{"name":"Intelligent Systems Lab, Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2912-3058","authenticated-orcid":false,"given":"Stamatis","family":"Chatzistamatis","sequence":"additional","affiliation":[{"name":"Intelligent Systems Lab, Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7006-1536","authenticated-orcid":false,"given":"George E.","family":"Tsekouras","sequence":"additional","affiliation":[{"name":"Intelligent Systems Lab, Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"El Saer","sequence":"additional","affiliation":[{"name":"ITML Co., 11524 Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chrisaphis","family":"Nathanailidis","sequence":"additional","affiliation":[{"name":"Lioncode Co., 64200 Kavala, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7838-9691","authenticated-orcid":false,"given":"Konstantinos","family":"Kotis","sequence":"additional","affiliation":[{"name":"Intelligent Systems Lab, Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1353\/lan.2021.0060","article-title":"Gender bias and stereotypes in linguistic example sentences","volume":"97","author":"Kotek","year":"2021","journal-title":"Language"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Menegatti, M., and Rubini, M. (2017). Gender Bias and Sexism in Language. Oxford Research Encyclopedia of Communication, Oxford University Press.","DOI":"10.1093\/acrefore\/9780190228613.013.470"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhou, P., Shi, W., Zhao, J., Huang, K.-H., Chen, M., Cotterell, R., and Chang, K.-W. (2019). Examining Gender Bias in Languages with Grammatical Gender. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1531"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Sun, T., Gaut, A., Tang, S., Huang, Y., ElSherief, M., Zhao, J., Mirza, D., Belding, E., Chang, K.-W., and Wang, W.Y. (2019). Mitigating Gender Bias in Natural Language Processing: Literature Review. arXiv.","DOI":"10.18653\/v1\/P19-1159"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lu, K., Mardziel, P., Wu, F., Amancharla, P., and Datta, A. (2020). Gender Bias in Neural Natural Language Processing. Logic, Language, and Security, Springer.","DOI":"10.1007\/978-3-030-62077-6_14"},{"key":"ref_6","unstructured":"Koroteev, M.V. (2021). BERT: A Review of Applications in Natural Language Processing and Understanding. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, E.Y., Cheok, A.D., Pan, Z., Cai, J., and Yan, Y. (2023). From Turing to Transformers: A Comprehensive Review and Tutorial on the Evolution and Applications of Generative Transformer Models. Sci, 5.","DOI":"10.3390\/sci5040046"},{"key":"ref_8","unstructured":"Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., and Kalai, A. (2016). Quantifying and Reducing Stereotypes in Word Embeddings. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Rao, P., and Taboada, M. (2021). Gender Bias in the News: A Scalable Topic Modelling and Visualization Framework. Front. Artif. Intell., 4.","DOI":"10.3389\/frai.2021.664737"},{"key":"ref_10","first-page":"1578","article-title":"Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval","volume":"7","author":"Wilson","year":"2024","journal-title":"Proc. AAAIACM Conf. AI Ethics Soc."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Matthews, A., Grasso, I., Mahoney, C., Chen, Y., Wali, E., Middleton, T., Njie, M., and Matthews, J. (2021). Gender Bias in Natural Language Processing Across Human Languages, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.trustnlp-1.6"},{"key":"ref_12","unstructured":"Lin, L., Wang, L., Guo, J., and Wong, K.-F. (2025). Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception. Proceedings of the 31st International Conference on Computational Linguistics, Association for Computational Linguistics. Available online: https:\/\/aclanthology.org\/2025.coling-main.709\/."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Dong, Q., Li, L., Dai, D., Zheng, C., Ma, J., Li, R., Xia, H., Xu, J., Wu, Z., and Chang, B.B. (2024). A Survey on In-context Learning. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hu, Y., Lee, C.-H., Xie, T., Yu, T., Smith, N.A., and Ostendorf, M. (2022). In-Context Learning for Few-Shot Dialogue State Tracking. arXiv.","DOI":"10.18653\/v1\/2022.findings-emnlp.193"},{"key":"ref_15","unstructured":"Prabhumoye, S., Kocielnik, R., Shoeybi, M., Anandkumar, A., and Catanzaro, B. (2021). Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases. arXiv."},{"key":"ref_16","unstructured":"Papantoniou, K., and Tzitzikas, Y. (2024). NLP for The Greek Language: A Longer Survey. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Papantoniou, K., and Tzitzikas, Y. (2020). NLP for the Greek Language: A Brief Survey. Proceedings of the 11th Hellenic Conference on Artificial Intelligence, Association for Computing Machinery.","DOI":"10.1145\/3411408.3411410"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Bakagianni, J., Pouli, K., Gavriilidou, M., and Pavlopoulos, J. (2024). A Systematic Survey of Natural Language Processing for the Greek Language. arXiv.","DOI":"10.1016\/j.patter.2025.101313"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Dimara, A., Kotis, K., Chatzistamatis, S., Evangeliou, N., Nathanailidis, C., and Tsekouras, G.E. (2025). Towards Effective Data Process Pipelines for Legal NLP in English and Non-English Languages: A Greek Case Study. Proceedings of the 2025 Computing, Communications and IoT Applications (ComComAp), IEEE.","DOI":"10.1109\/ComComAp68359.2025.11353184"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Dimara, A., Kotis, K., Papaioannou, A., Chatzistamatis, S., Evangeliou, N., Nathanailidis, C., and Tsekouras, G. (2025). Data Collection, Organization, and Privacy-Preserving Preparation for Edge-Based LLMs in Legal Text Analytics. Proceedings of the 2025 5th International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), IEEE.","DOI":"10.1109\/ICECCME64568.2025.11277858"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zmigrod, R., Mielke, S.J., Wallach, H., and Cotterell, R. (2019). Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics.","DOI":"10.18653\/v1\/P19-1161"},{"key":"ref_22","first-page":"619","article-title":"Gender bias in machine learning: Insights from official labour statistics and textual analysis","volume":"60","author":"Filandrianos","year":"2026","journal-title":"Qual. Quant."},{"key":"ref_23","unstructured":"Doughman, J., and Khreich, W. (2022). Gender Bias in Text: Labeled Datasets and Lexicons. arXiv."},{"key":"ref_24","unstructured":"Stanczak, K., and Augenstein, I. (2021). A Survey on Gender Bias in Natural Language Processing. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Derner, E., de la Fuente, S.S., Guti\u00e9rrez, Y., Moreda, P., and Oliver, N. (2024). Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora 2025. arXiv.","DOI":"10.18653\/v1\/2025.gebnlp-1.39"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhao, J., Zhou, Y., Li, Z., Wang, W., and Chang, K.-W. (2018). Learning Gender-Neutral Word Embeddings. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-1521"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1007\/s40747-025-01859-z","article-title":"Genderly: A data-centric gender bias detection system","volume":"11","author":"Khreich","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Shrestha, I., and Srinivasan, P. (2025). LLM Bias Detection and Mitigation through the Lens of Desired Distributions. arXiv.","DOI":"10.18653\/v1\/2025.emnlp-main.76"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ratovicius, C.J., Diaz-Pace, J.A., and Tommasel, A. (2024). Detection of Gender Bias in Legal Texts Using Classification and LLMs. Proceedings of the 2024 L Latin American Computer Conference (CLEI), IEEE.","DOI":"10.1109\/CLEI64178.2024.10700116"},{"key":"ref_30","unstructured":"Thakur, V. (2023). Unveiling Gender Bias in Terms of Profession Across LLMs: Analyzing and Addressing Sociological Implications. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wan, Y., Pu, G., Sun, J., Garimella, A., Chang, K.-W., and Peng, N. (2023). \u201cKelly is a Warm Person, Joseph is a Role Model\u201d: Gender Biases in LLM-Generated Reference Letters. arXiv.","DOI":"10.18653\/v1\/2023.findings-emnlp.243"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1145\/3596490","article-title":"Shortcut Learning of Large Language Models in Natural Language Understanding","volume":"67","author":"Du","year":"2024","journal-title":"Commun. ACM"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Mousavian, M., Abbasiantaeb, Z., Aliannejadi, M., and Crestani, F. (2025). Towards Fair Rankings: Leveraging LLMs for Gender Bias Detection and Measurement. Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR), ACM.","DOI":"10.1145\/3731120.3744620"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Amrhein, C., Schottmann, F., Sennrich, R., and L\u00e4ubli, S. (2023). Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model. arXiv.","DOI":"10.18653\/v1\/2023.acl-long.246"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zipperling, D., Deck, L., Lanzl, J., and K\u00fchl, N. (2025). It\u2019s only fair when I think it\u2019s fair: How Gender Bias Alignment Undermines Distributive Fairness in Human-AI Collaboration. Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, ACM.","DOI":"10.1145\/3715275.3732084"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Cheng, X., Zan, H., Kong, L., Song, J., and Peng, M. (2025). Detection, Classification, and Mitigation of Gender Bias in Large Language Models. arXiv.","DOI":"10.1007\/978-981-95-3352-7_42"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3628602","article-title":"Measuring and Mitigating Gender Bias in Legal Contextualized Language Models","volume":"18","author":"Bozdag","year":"2024","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Spinelli, E., Chevrot, J.-P., and Varnet, L. (2023). Neutral is not fair enough: Testing the efficiency of different language gender-fair strategies. Front. Psychol., 14.","DOI":"10.3389\/fpsyg.2023.1256779"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1017\/S1351324922000122","article-title":"Gender bias in legal corpora and debiasing it","volume":"29","author":"Sevim","year":"2023","journal-title":"Nat. Lang. Eng."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Mirza, I., Jafari, A.A., Ozcinar, C., and Anbarjafari, G. (2025). Quantifying Gender Bias in Large Language Models Using Information-Theoretic and Statistical Analysis. Information, 16.","DOI":"10.3390\/info16050358"},{"key":"ref_41","unstructured":"Kumar, S.H., Sahay, S., Mazumder, S., Okur, E., Manuvinakurike, R., Beckage, N., Su, H., Lee, H., and Nachman, L. (2024). Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"132498","DOI":"10.1016\/j.neucom.2025.132498","article-title":"A differentiable and uncertainty-aware mutual information regularizer for bias mitigation","volume":"669","author":"Incremona","year":"2026","journal-title":"Neurocomputing"},{"key":"ref_43","unstructured":"Flach, P.A., De Bie, T., and Cristianini, N. (2012). Fairness-Aware Classifier with Prejudice Remover Regularizer. Proceedings of the Machine Learning and Knowledge Discovery in Databases, Springer."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhang, B.H., Lemoine, B., and Mitchell, M. (2018). Mitigating Unwanted Biases with Adversarial Learning. Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society, ACM.","DOI":"10.1145\/3278721.3278779"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Ghassami, A., Khodadadian, S., and Kiyavash, N. (2018). Fairness in Supervised Learning: An Information Theoretic Approach. arXiv.","DOI":"10.1109\/ISIT.2018.8437807"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Bodicoat, A., Terragni, V., and Jahangirova, G. (2025, January 19\u201320). Replication Package for: Understanding LLM-Driven Test Oracle Generation. Proceedings of the AIware 2025\u20142nd ACM International Conference on AI-powered Software, Seoul, Republic of Korea.","DOI":"10.1109\/AIware69974.2025.00011"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., and Zettlemoyer, L. (2022). Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.emnlp-main.759"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/4\/342\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T09:37:58Z","timestamp":1775122678000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/4\/342"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["info17040342"],"URL":"https:\/\/doi.org\/10.3390\/info17040342","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]}}}