Salvato in:
Dettagli Bibliografici
Autori principali: Peña, Alejandro, Fierrez, Julian, Morales, Aythami, Mancera, Gonzalo, Lopez, Miguel, Tolosana, Ruben
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.11880
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909648575004672
author Peña, Alejandro
Fierrez, Julian
Morales, Aythami
Mancera, Gonzalo
Lopez, Miguel
Tolosana, Ruben
author_facet Peña, Alejandro
Fierrez, Julian
Morales, Aythami
Mancera, Gonzalo
Lopez, Miguel
Tolosana, Ruben
contents The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical concerns, such as demographic biases, accountability, or privacy. This work seeks to analyze the capacity of Transformers-based systems to learn demographic biases present in the data, using a case study on AI-based automated recruitment. We propose a privacy-enhancing framework to reduce gender information from the learning pipeline as a way to mitigate biased behaviors in the final tools. Our experiments analyze the influence of data biases on systems built on two different LLMs, and how the proposed framework effectively prevents trained systems from reproducing the bias in the data.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11880
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment
Peña, Alejandro
Fierrez, Julian
Morales, Aythami
Mancera, Gonzalo
Lopez, Miguel
Tolosana, Ruben
Artificial Intelligence
Computation and Language
The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical concerns, such as demographic biases, accountability, or privacy. This work seeks to analyze the capacity of Transformers-based systems to learn demographic biases present in the data, using a case study on AI-based automated recruitment. We propose a privacy-enhancing framework to reduce gender information from the learning pipeline as a way to mitigate biased behaviors in the final tools. Our experiments analyze the influence of data biases on systems built on two different LLMs, and how the proposed framework effectively prevents trained systems from reproducing the bias in the data.
title Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2506.11880