Sergio Morales
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sergio Morales has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Robert Clarisó
Universitat Oberta de Catalunya, Barcelona, Spain
9 shared publications - Jordi Cabot
Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg and University of Luxembourg, Esch-sur-Alzette, Luxembourg
8 shared publications - Bilal Said
Softeam, Nantes, France
1 shared publication - Elena Planas
Universitat Oberta de Catalunya, Barcelona, Spain
1 shared publication - Hugo Bruneliere
IMT Atlantique, LS2N (UMR CNRS 6004), Nantes, France
1 shared publication - Marc Oriol
Universitat Politecnica de Catalunya
1 shared publication
Latest Publications
- Open Access
- 24 September 2026
- Published by Springer Nature in Software and Systems Modeling
- p. 1-30
LangBiTe: model-driven bias testing of text-to-text large language models
- 24 September 2026
- Published by Springer Nature in Software and Systems Modeling
- p. 1-30
Open AccessLangBiTe: model-driven bias testing of text-to-text large language models
- Open Access
- 23 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 95-102
Robust LLM-as-a-Judge Validators for Assessing the Quality of Educational Exams
Although promising, the integration of Large Language Models into educational products brings some risks that companies must mitigate. In this paper, we discuss a set of quality criteria (e.g. correctness and clarity), grounded in the literature and validated by our industrial partner, relevant for designing educational exams. We also present a set of validators, using an LLM-as-a-judge approach, to automatically check the quality of educational exams. We evaluate their robustness on quality and (artificially generated) defective educational items, including 17 commercial and open-source LLMs. Our experiments show that the most recent and larger models are very precise, trigger almost no false alarms, and are effective in detecting most quality issues. Moreover, open source Llama and DeepSeek models perform as well as GPT models, although Mistral seems unsuitable for this task. The promising results encourage us to focus on more general types of questions, for which we report relevant open challenges we aim to address in the short term.
- 23 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 95-102
Open AccessRobust LLM-as-a-Judge Validators for Assessing the Quality of Educational Exams
Although promising, the integration of Large Language Models into educational products brings some risks that companies must mitigate. In this paper, we discuss a set of quality criteria (e.g. correctness and clarity), grounded in the literature and validated by our industrial partner, relevant for designing educational exams. We also present a set of validators, using an LLM-as-a-judge approach, to automatically check the quality of educational exams. We evaluate their robustness on quality and (artificially generated) defective educational items, including 17 commercial and open-source LLMs. Our experiments show that the most recent and larger models are very precise, trigger almost no false alarms, and are effective in detecting most quality issues. Moreover, open source Llama and DeepSeek models perform as well as GPT models, although Mistral seems unsuitable for this task. The promising results encourage us to focus on more general types of questions, for which we report relevant open challenges we aim to address in the short term.
- Open Access
- 27 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 95-106
ImageBiTe: A Framework for Evaluating Representational Harms in Text-to-Image Models
Advances in online text-to-image (T2I) generator models allow users and organizations alike to generate millions of images from text prompts. Unfortunately, recent studies have demonstrated how elementary prompts result in displaying noticeable social biases in the models' output imagery. The potential representational harm of T2I models could lead to further marginalize minority groups. Thus, a systematic approach is required to comprehensively and continuously assess the absence of bias in T2I generators. In this paper, we present ImageBiTe, a framework to systematically and thoroughly evaluate representational discrimination in T2I-generated images, seamlessly integrable into AI engineering processes. ImageBiTe enables development teams to customize their test scenarios and automatically create and run test cases based on user-defined non-discrimination requirements. We have implemented an open-source tool, available on GitHub, to support the application of our approach.
- 27 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 95-106
Open AccessImageBiTe: A Framework for Evaluating Representational Harms in Text-to-Image Models
Advances in online text-to-image (T2I) generator models allow users and organizations alike to generate millions of images from text prompts. Unfortunately, recent studies have demonstrated how elementary prompts result in displaying noticeable social biases in the models' output imagery. The potential representational harm of T2I models could lead to further marginalize minority groups. Thus, a systematic approach is required to comprehensively and continuously assess the absence of bias in T2I generators. In this paper, we present ImageBiTe, a framework to systematically and thoroughly evaluate representational discrimination in T2I-generated images, seamlessly integrable into AI engineering processes. ImageBiTe enables development teams to customize their test scenarios and automatically create and run test cases based on user-defined non-discrimination requirements. We have implemented an open-source tool, available on GitHub, to support the application of our approach.
- Open Access
- 15 January 2025
- Published by Springer Nature in Software and Systems Modeling
- Vol. 24 (6) , 1627-1645
Impromptu: a framework for model-driven prompt engineering
Generative artificial intelligence (AI) systems are capable of synthesizing complex artifacts such as text, source code or images according to the instructions provided in a natural language prompt. The quality of the input prompt, in terms of both content and structure, has a large impact on the quality of the output. This has given rise to prompt engineering , the process of designing natural language prompts to best take advantage of the capabilities of generative AI systems. This paper describes , a model-driven engineering framework to support the creation, management and reuse of prompts for generative AI. offers a domain-specific language (DSL) to define multimodal prompts in a modular and tool-independent way. The language offers additional features such as versioning, prompt chaining and multi-language support. Moreover, it provides tool support to adapt prompts for specific generative AI systems, execute those prompts on a generative AI system and validate the quality of the response that is generated. is available as a Langium-based Visual Studio Code plugin.
- 15 January 2025
- Published by Springer Nature in Software and Systems Modeling
- Vol. 24 (6) , 1627-1645
Open AccessImpromptu: a framework for model-driven prompt engineering
Generative artificial intelligence (AI) systems are capable of synthesizing complex artifacts such as text, source code or images according to the instructions provided in a natural language prompt. The quality of the input prompt, in terms of both content and structure, has a large impact on the quality of the output. This has given rise to prompt engineering , the process of designing natural language prompts to best take advantage of the capabilities of generative AI systems. This paper describes , a model-driven engineering framework to support the creation, management and reuse of prompts for generative AI. offers a domain-specific language (DSL) to define multimodal prompts in a modular and tool-independent way. The language offers additional features such as versioning, prompt chaining and multi-language support. Moreover, it provides tool support to adapt prompts for specific generative AI systems, execute those prompts on a generative AI system and validate the quality of the response that is generated. is available as a Langium-based Visual Studio Code plugin.
- Open Access
- 22 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 203-213
A DSL for Testing LLMs for Fairness and Bias
Large language models (LLMs) are increasingly integrated into software systems to enhance them with generative AI capabilities. But LLMs may reflect a biased behavior, resulting in systems that could discriminate against gender, age or ethnicity, among other ethical concerns. Society and upcoming regulations will force companies and development teams to ensure their AI-enhanced software is ethically fair. To facilitate such ethical assessment, we propose LangBiTe, a model-driven solution to specify ethical requirements, and customize and automate the testing of ethical biases in LLMs. The evaluation can raise awareness on the biases of the LLM-based components of the system and/or trigger a change in the LLM of choice based on the requirements of that particular application. The model-driven approach makes both the requirements specification and the test generation platform-independent, and provides end-to-end traceability between the requirements and their assessment. We have implemented an open-source tool set, available on GitHub, to support the application of our approach.
- 22 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 203-213
Open AccessA DSL for Testing LLMs for Fairness and Bias
Large language models (LLMs) are increasingly integrated into software systems to enhance them with generative AI capabilities. But LLMs may reflect a biased behavior, resulting in systems that could discriminate against gender, age or ethnicity, among other ethical concerns. Society and upcoming regulations will force companies and development teams to ensure their AI-enhanced software is ethically fair. To facilitate such ethical assessment, we propose LangBiTe, a model-driven solution to specify ethical requirements, and customize and automate the testing of ethical biases in LLMs. The evaluation can raise awareness on the biases of the LLM-based components of the system and/or trigger a change in the LLM of choice based on the requirements of that particular application. The model-driven approach makes both the requirements specification and the test generation platform-independent, and provides end-to-end traceability between the requirements and their assessment. We have implemented an open-source tool set, available on GitHub, to support the application of our approach.
- Open Access
- 2 August 2024
- Published by Elsevier in Journal of Systems and Software
- Vol. 217
An architecture for model-based and intelligent automation in DevOps
- 2 August 2024
- Published by Elsevier in Journal of Systems and Software
- Vol. 217
Open AccessAn architecture for model-based and intelligent automation in DevOps
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 110-113
Generative AI in Model-Driven Software Engineering Education: Friend or Foe?
The availability and effectiveness of generative AI tools challenge the currently established methods for learning, teaching and assessment. In this paper, we discuss their potential impact for model-driven software engineering education, both from the point of view of educators and students. The discussion highlights several opportunities and risks, which support the need of a critical perspective in the application of these tools.
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 110-113
Generative AI in Model-Driven Software Engineering Education: Friend or Foe?
The availability and effectiveness of generative AI tools challenge the currently established methods for learning, teaching and assessment. In this paper, we discuss their potential impact for model-driven software engineering education, both from the point of view of educators and students. The discussion highlights several opportunities and risks, which support the need of a critical perspective in the application of these tools.
- 11 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1705-1707
Automating Bias Testing of LLMs
Large Language Models (LLMs) are being quickly integrated in a myriad of software applications. This may introduce a number of biases, such as gender, age or ethnicity, in the behavior of such applications. To face this challenge, we explore the automatic generation of tests suites to assess the potential biases of an LLM. Each test is defined as a prompt used as input to the LLM and a test oracle that analyses the LLM output to detect the presence of biases.
- 11 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1705-1707
Automating Bias Testing of LLMs
Large Language Models (LLMs) are being quickly integrated in a myriad of software applications. This may introduce a number of biases, such as gender, age or ethnicity, in the behavior of such applications. To face this challenge, we explore the automatic generation of tests suites to assess the potential biases of an LLM. Each test is defined as a prompt used as input to the LLM and a test oracle that analyses the LLM output to detect the presence of biases.
- 14 November 2022
- Published by Springer Nature
- p. 53-60
Towards a DSL for AI Engineering Process Modeling
- 14 November 2022
- Published by Springer Nature
- p. 53-60
Towards a DSL for AI Engineering Process Modeling