Alejandro Peña
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alejandro Peña has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Aythami Morales
Universidad Autónoma de Madrid (UAM)
12 shared publications - Julian Fierrez
Universidad Autónoma de Madrid (UAM)
12 shared publications - Javier Ortega-Garcia
Universidad Autónoma de Madrid
5 shared publications - Ruben Tolosana
Universidad Autónoma de Madrid
5 shared publications - Ignacio Serna
School of Engineering Universidad Autonoma de Madrid Spain
4 shared publications - Ainhoa Herrarte
Universidad Autónoma de Madrid
2 shared publications
Latest Publications
- 24 November 2025
- Published by Springer Nature
- p. 3-20
PBa-LLM: Privacy- and Bias-Aware NLP Using Named-Entity Recognition (NER)
- 24 November 2025
- Published by Springer Nature
- p. 3-20
PBa-LLM: Privacy- and Bias-Aware NLP Using Named-Entity Recognition (NER)
- Open Access
- 15 October 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
- Vol. 8 (2) , 1976-1987
Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment
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.
- 15 October 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
- Vol. 8 (2) , 1976-1987
Open AccessAddressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment
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.
- 2 December 2024
- Published by Springer Nature
- p. 110-126
Comprehensive Equity Index (CEI): Definition and Application to Bias Evaluation in Biometrics
- 2 December 2024
- Published by Springer Nature
- p. 110-126
Comprehensive Equity Index (CEI): Definition and Application to Bias Evaluation in Biometrics
- Open Access
Comprehensive Equity Index (CEI): Definition and Application to Bias Evaluation in Biometrics
We present a novel metric designed, among other applications, to quantify biased behaviors of machine learning models. As its core, the metric consists of a new similarity metric between score distributions that balances both their general shapes and tails' probabilities. In that sense, our proposed metric may be useful in many application areas. Here we focus on and apply it to the operational evaluation of face recognition systems, with special attention to quantifying demographic biases; an application where our metric is especially useful. The topic of demographic bias and fairness in biometric recognition systems has gained major attention in recent years. The usage of these systems has spread in society, raising concerns about the extent to which these systems treat different population groups. A relevant step to prevent and mitigate demographic biases is first to detect and quantify them. Traditionally, two approaches have been studied to quantify differences between population groups in machine learning literature: 1) measuring differences in error rates, and 2) measuring differences in recognition score distributions. Our proposed Comprehensive Equity Index (CEI) trade-offs both approaches combining both errors from distribution tails and general distribution shapes. This new metric is well suited to real-world scenarios, as measured on NIST FRVT evaluations, involving high-performance systems and realistic face databases including a wide range of covariates and demographic groups. We first show the limitations of existing metrics to correctly assess the presence of biases in realistic setups and then propose our new metric to tackle these limitations. We tested the proposed metric with two state-of-the-art models and four widely used databases, showing its capacity to overcome the main flaws of previous bias metrics.
Open AccessComprehensive Equity Index (CEI): Definition and Application to Bias Evaluation in Biometrics
We present a novel metric designed, among other applications, to quantify biased behaviors of machine learning models. As its core, the metric consists of a new similarity metric between score distributions that balances both their general shapes and tails' probabilities. In that sense, our proposed metric may be useful in many application areas. Here we focus on and apply it to the operational evaluation of face recognition systems, with special attention to quantifying demographic biases; an application where our metric is especially useful. The topic of demographic bias and fairness in biometric recognition systems has gained major attention in recent years. The usage of these systems has spread in society, raising concerns about the extent to which these systems treat different population groups. A relevant step to prevent and mitigate demographic biases is first to detect and quantify them. Traditionally, two approaches have been studied to quantify differences between population groups in machine learning literature: 1) measuring differences in error rates, and 2) measuring differences in recognition score distributions. Our proposed Comprehensive Equity Index (CEI) trade-offs both approaches combining both errors from distribution tails and general distribution shapes. This new metric is well suited to real-world scenarios, as measured on NIST FRVT evaluations, involving high-performance systems and realistic face databases including a wide range of covariates and demographic groups. We first show the limitations of existing metrics to correctly assess the presence of biases in realistic setups and then propose our new metric to tackle these limitations. We tested the proposed metric with two state-of-the-art models and four widely used databases, showing its capacity to overcome the main flaws of previous bias metrics.
- Open Access
- 15 April 2024
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 27 (2) , 1-19
Spatio-temporal trajectory data modeling for fishing gear classification
International Organizations urge the protection of our oceans and their ecosystems due to their immeasurable importance to humankind. Since illegal fishing activities, commonly known as IUU fishing, cause irreparable damage to these ecosystems, concerned organisms are pushing to detect and combat IUU fishing practices. The automatic identification system allows to locate the position and trajectory of fishing vessels. In this study we address the task of detecting vessels’ fishing gears based on the trajectory behavior defined by GPS position data, a useful task to prevent the proliferation of IUU fishing practices. We present a new database including trajectories that span 7 different fishing gears and analyze these as in a time sequence analysis problem. We leverage from feature extraction techniques from the online signature verification domain to model vessel trajectories, and extract relevant information in the form of both local and global feature sets. We show how, based on these sets of features, the kinematics of vessels according to different fishing gears can be effectively classified using common supervised learning algorithms with accuracies up to $$90\%$$ . Furthermore, motivated by the concerns raised by several organizations on the adverse impact of bottom trawling on marine biodiversity, we present a binary classification experiment in which we were able to distinguish this kind of fishing gear with an accuracy of $$99\%$$ . We also illustrate in an ablation study the relevance of factors such as data availability and the sampling period to perform fishing gear classification. Compared to existing works, we highlight these factors, especially the importance of using sampling periods in the order of minutes instead of hours.- 15 April 2024
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 27 (2) , 1-19
Open AccessSpatio-temporal trajectory data modeling for fishing gear classification
International Organizations urge the protection of our oceans and their ecosystems due to their immeasurable importance to humankind. Since illegal fishing activities, commonly known as IUU fishing, cause irreparable damage to these ecosystems, concerned organisms are pushing to detect and combat IUU fishing practices. The automatic identification system allows to locate the position and trajectory of fishing vessels. In this study we address the task of detecting vessels’ fishing gears based on the trajectory behavior defined by GPS position data, a useful task to prevent the proliferation of IUU fishing practices. We present a new database including trajectories that span 7 different fishing gears and analyze these as in a time sequence analysis problem. We leverage from feature extraction techniques from the online signature verification domain to model vessel trajectories, and extract relevant information in the form of both local and global feature sets. We show how, based on these sets of features, the kinematics of vessels according to different fishing gears can be effectively classified using common supervised learning algorithms with accuracies up to $$90\%$$ . Furthermore, motivated by the concerns raised by several organizations on the adverse impact of bottom trawling on marine biodiversity, we present a binary classification experiment in which we were able to distinguish this kind of fishing gear with an accuracy of $$99\%$$ . We also illustrate in an ablation study the relevance of factors such as data availability and the sampling period to perform fishing gear classification. Compared to existing works, we highlight these factors, especially the importance of using sampling periods in the order of minutes instead of hours. - Open Access
- 6 April 2024
- Published by Elsevier in Information Fusion
- Vol. 108
Continuous document layout analysis: Human-in-the-loop AI-based data curation, database, and evaluation in the domain of public affairs
- 6 April 2024
- Published by Elsevier in Information Fusion
- Vol. 108
Open AccessContinuous document layout analysis: Human-in-the-loop AI-based data curation, database, and evaluation in the domain of public affairs
- 15 August 2023
- Published by Springer Nature
- p. 123-138
Document Layout Annotation: Database and Benchmark in the Domain of Public Affairs
- 15 August 2023
- Published by Springer Nature
- p. 123-138
Document Layout Annotation: Database and Benchmark in the Domain of Public Affairs
- Top Cited Papers
- 15 August 2023
- Published by Springer Nature
- p. 20-33
Leveraging Large Language Models for Topic Classification in the Domain of Public Affairs
- 15 August 2023
- Published by Springer Nature
- p. 20-33
Top Cited PapersLeveraging Large Language Models for Topic Classification in the Domain of Public Affairs
- Open Access
- 7 June 2023
- Published by Springer Nature in SN Computer Science
- Vol. 4 (5) , 1-20
Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-Based Recruitment
The presence of decision-making algorithms in society is rapidly increasing nowadays, while concerns about their transparency and the possibility of these algorithms becoming new sources of discrimination are arising. There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good; (ii) privacy and data ownership; (iii) transparency and accountability; and (iv) fairness in AI-driven decision-making processes. All these four Human-Centric requirements are closely related to each other. With the aim of studying how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data, we propose a fictitious case study focused on automated recruitment: FairCVtest. We train automatic recruitment algorithms using a set of multimodal synthetic profiles including image, text, and structured data, which are consciously scored with gender and racial biases. FairCVtest shows the capacity of the Artificial Intelligence (AI) behind automatic recruitment tools built this way (a common practice in many other application scenarios beyond recruitment) to extract sensitive information from unstructured data and exploit it in combination to data biases in undesirable (unfair) ways. We present an overview of recent works developing techniques capable of removing sensitive information and biases from the decision-making process of deep learning architectures, as well as commonly used databases for fairness research in AI. We demonstrate how learning approaches developed to guarantee privacy in latent spaces can lead to unbiased and fair automatic decision-making process. Our methodology and results show how to generate fairer AI-based tools in general, and in particular fairer automated recruitment systems.
- 7 June 2023
- Published by Springer Nature in SN Computer Science
- Vol. 4 (5) , 1-20
Open AccessHuman-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-Based Recruitment
The presence of decision-making algorithms in society is rapidly increasing nowadays, while concerns about their transparency and the possibility of these algorithms becoming new sources of discrimination are arising. There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good; (ii) privacy and data ownership; (iii) transparency and accountability; and (iv) fairness in AI-driven decision-making processes. All these four Human-Centric requirements are closely related to each other. With the aim of studying how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data, we propose a fictitious case study focused on automated recruitment: FairCVtest. We train automatic recruitment algorithms using a set of multimodal synthetic profiles including image, text, and structured data, which are consciously scored with gender and racial biases. FairCVtest shows the capacity of the Artificial Intelligence (AI) behind automatic recruitment tools built this way (a common practice in many other application scenarios beyond recruitment) to extract sensitive information from unstructured data and exploit it in combination to data biases in undesirable (unfair) ways. We present an overview of recent works developing techniques capable of removing sensitive information and biases from the decision-making process of deep learning architectures, as well as commonly used databases for fairness research in AI. We demonstrate how learning approaches developed to guarantee privacy in latent spaces can lead to unbiased and fair automatic decision-making process. Our methodology and results show how to generate fairer AI-based tools in general, and in particular fairer automated recruitment systems.
- Open Access
Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment
The presence of decision-making algorithms in society is rapidly increasing nowadays, while concerns about their transparency and the possibility of these algorithms becoming new sources of discrimination are arising. There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good; (ii) privacy and data ownership; (iii) transparency and accountability; and (iv) fairness in AI-driven decision-making processes. All these four Human-Centric requirements are closely related to each other. With the aim of studying how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data, we propose a fictitious case study focused on automated recruitment: FairCVtest. We train automatic recruitment algorithms using a set of multimodal synthetic profiles including image, text, and structured data, which are consciously scored with gender and racial biases. FairCVtest shows the capacity of the Artificial Intelligence (AI) behind automatic recruitment tools built this way (a common practice in many other application scenarios beyond recruitment) to extract sensitive information from unstructured data and exploit it in combination to data biases in undesirable (unfair) ways. We present an overview of recent works developing techniques capable of removing sensitive information and biases from the decision-making process of deep learning architectures, as well as commonly used databases for fairness research in AI. We demonstrate how learning approaches developed to guarantee privacy in latent spaces can lead to unbiased and fair automatic decision-making process.
Open AccessHuman-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment
The presence of decision-making algorithms in society is rapidly increasing nowadays, while concerns about their transparency and the possibility of these algorithms becoming new sources of discrimination are arising. There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good; (ii) privacy and data ownership; (iii) transparency and accountability; and (iv) fairness in AI-driven decision-making processes. All these four Human-Centric requirements are closely related to each other. With the aim of studying how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data, we propose a fictitious case study focused on automated recruitment: FairCVtest. We train automatic recruitment algorithms using a set of multimodal synthetic profiles including image, text, and structured data, which are consciously scored with gender and racial biases. FairCVtest shows the capacity of the Artificial Intelligence (AI) behind automatic recruitment tools built this way (a common practice in many other application scenarios beyond recruitment) to extract sensitive information from unstructured data and exploit it in combination to data biases in undesirable (unfair) ways. We present an overview of recent works developing techniques capable of removing sensitive information and biases from the decision-making process of deep learning architectures, as well as commonly used databases for fairness research in AI. We demonstrate how learning approaches developed to guarantee privacy in latent spaces can lead to unbiased and fair automatic decision-making process.