{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:22:35Z","timestamp":1780464155362,"version":"3.54.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIES"],"abstract":"<jats:p>The use of language technologies in high-stake settings is\nincreasing in recent years, mostly motivated by the success\nof Large Language Models (LLMs). However, despite the great\nperformance of LLMs, they are are susceptible to ethical\nconcerns, such as demographic biases, accountability, or\nprivacy. This work seeks to analyze the capacity of\nTransformers-based systems to learn demographic biases\npresent in the data, using a case study on AI-based\nautomated recruitment. We propose a privacy-enhancing\nframework to reduce gender information from the learning\npipeline as a way to mitigate biased behaviors in the final\ntools. Our experiments analyze the influence of data biases\non systems built on two different LLMs, and how the\nproposed framework effectively prevents trained systems\nfrom reproducing the bias in the data.<\/jats:p>","DOI":"10.1609\/aies.v8i2.36689","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:20:47Z","timestamp":1760534447000},"page":"1976-1987","source":"Crossref","is-referenced-by-count":6,"title":["Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment"],"prefix":"10.1609","volume":"8","author":[{"given":"Alejandro","family":"Pe\u00f1a","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Fierrez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aythami","family":"Morales","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gonzalo","family":"Mancera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miguel","family":"Lopez-Duran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruben","family":"Tolosana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"9382","published-online":{"date-parts":[[2025,10,15]]},"container-title":["Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36689\/38827","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36689\/38827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:20:47Z","timestamp":1760534447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/view\/36689"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":0,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,10,15]]}},"URL":"https:\/\/doi.org\/10.1609\/aies.v8i2.36689","relation":{},"ISSN":["3065-8365"],"issn-type":[{"value":"3065-8365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}