Engineering fairness in complex (software) world

The FRINGE (context-aware FaiRness engineerING in complex software systEms) project studies solutions for engineering software fairness in the context of ML-Intensive systems.

Aims and scope

Machine learning (ML) pervades our daily lives, being embedded in any kind of device, service, and/or system, and enabling complex data-driven decision-making solutions. By 2025, over 463 exabytes of data will be generated daily and the digital transformation will further increase the pervasiveness of ML solutions and the subsequent risk that those solutions may unethically exploit sensitive pieces of data, potentially leading to forms of discrimination. This is why the European Union, through the Artificial Intelligence Act (https://artificialintelligenceact.eu/), raised the concern of having novel solutions to ensure trustworthy and ethical artificial intelligence able to protect ethical principles.

The overarching goal of the project is to provide software engineers, data scientists, and ML experts with a comprehensive set of methodologies, approaches, and software engineering (SE) solutions to improve the development, monitoring, and design of fairness-related properties of ML-intensive systems. FRINGE will help to sustain the digital transformation by empowering advanced artificial intelligence applications through instruments that can lead to the trustworthy and ethical exploitation of large amounts of data. More specifically, FRINGE aims to conceive:

  • a metamodel for ML fairness;
  • a fairness-aware monitoring infrastructure for ML-intensive systems
  • solutions able to exploit contextual information to recommend and spot issues with fairness definitions, requirements and specifications for the specific task at hand;
  • design pattern recommenders and antipattern detection approaches.

Publications

2025

  • Best paper award Tosin Fadahunsi, Giordano d'Aloisio, Antinisca Di Marco, and Federica Sarro 2025. How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias. The Proceedings of the 1st International Workshop on Fairness in Software Systems, to appear. Replication package

  • Riccardo Rubei, Aicha Moussaid, Claudio di Sipio, and Davide di Ruscio 2025. Prompt engineering and its implications on the energy consumption of Large Language Models. The Proceedings of 9th International Workshop on Green and Sustainable Software (GREENS’25), to appear. Replication package

  • Claudio Di Sipio, Juri Di Rocco, Davide Di Ruscio, and Vladyslav Bulhakov 2025. Addressing Popularity Bias in Third-Party Library Recommendations Using LLMs. The Proceedings of the 1st International Workshop on Fairness in Software Systems, to appear. Replication package

  • Juri Di Rocco, Davide Di Ruscio, Claudio Di Sipio, Phuong T. Nguyen and, Riccardo Rubei 2025. On the use of large language models in model-driven engineering. Software and Systems Modeling, 1-26. Replication package

  • Juri Di Rocco, Phuong T. Nguyen, Claudio Di Sipio, Riccardo Rubei, Davide Di Ruscio, and Massimiliano Di Penta, 2025. DeepMig: A Transformer-based Approach to Support Coupled Library and Code Migrations. Information and Software Technology, Volume 177, 2024, 107588, ISSN 0950-5849. Replication package

  • Best paper award Alessandra Parziale, Gianmario Voria, Giammaria Giordano, Gemma Catolino, Gregorio Robles, and Fabio Palomba 2025. Contextual Fairness-Aware Practices in ML: A Cost-Effective Empirical Evaluation. The Proceedings of the 1st International Workshop on Fairness in Software Systems, to appear. Replication package

  • Gregorio Dalia, Andrea Di Sorbo, Corrado A. Visaggio, Gerardo Canfora 2025. It’s Acting Odd! Exploring Equivocal Behaviors of Goodware International Conference on the Foundations of Software Engineering, to appear.

  • Giordano d'Aloisio, Claudio Di Sipio, Antinisca Di Marco, and Davide Di Ruscio 2025. How fair are we? From conceptualization to automated assessment of fairness definitions Software and Systems Modeling, 1-27 Replication package

2024

  • Gianmario Voria, Stefano Lambiase , Maria Concetta Schiavone, Gemma Catolino, and Fabio Palomba. 2024. From Expectation to Habit: Why Do Software Practitioners Adopt Fairness Toolkits?. The Proceedings of the 1st International Workshop on Fairness in Software Systems, to appear. Replication package

  • Dario Di Dario, Viviana Pentangelo, Maria Immacolata Colella, Fabio Palomba, and Carmine Gravino. 2024. Collecting and Implementing Ethical Guidelines for Emotion Recognition in an Educational Metaverse. In Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization (UMAP Adjunct '24). Association for Computing Machinery, New York, NY, USA, 549–554.

  • Carmine Ferrara, Francesco Casillo, Carmine Gravino, Andrea De Lucia, and Fabio Palomba. 2024. ReFAIR: Toward a Context-Aware Recommender for Fairness Requirements Engineering. In Proceedings of the IEEE/ACM 46th International Conference on Software Engineering (ICSE '24). Association for Computing Machinery, New York, NY, USA, Article 213, 1–12. Replication package

  • Gianmario Voria, Gemma Catolino, and Fabio Palomba. 2024. Is Attention All You Need? Toward a Conceptual Model for Social Awareness in Large Language Models. In Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering (FORGE '24). Association for Computing Machinery, New York, NY, USA, 69–73.

  • Claudio Di Sipio, Riccardo Rubei, Juri Di Rocco, Davide Di Ruscio, and Phuong T. Nguyen. 2024. Automated categorization of pre-trained models in software engineering: A case study with a Hugging Face dataset. In Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering (EASE '24). Association for Computing Machinery, New York, NY, USA, 351–356. Replication package

  • Fabio Palomba, Andrea Di Sorbo, Davide Di Ruscio, Filomena Ferrucci, Gemma Catolino, Giammaria Giordano, Dario Di Dario, Gianmario Voria, Viviana Pentangelo, Maria Tortorella, Arnaldo Sgueglia, Claudio Di Sipio, Giordano D'Aloisio, and Antinisca Di Marco. 2024. FRINGE: context-aware FaiRness engineerING in complex software systEms. In Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM '24). Association for Computing Machinery, New York, NY, USA, 608–612.

  • Rickson Simioni Pereira, Claudio Di Sipio, Martina De Sanctis, and Ludovico Iovino. 2024. On the Need for Configurable Travel Recommender Systems: A Systematic Mapping Study. 50th Euromicro Conference Series on Software Engineering and Advanced Applications (SEAA) 2024. Replication package

  • Phoung T. Nguyen, Juri Di Rocco, Claudio Di Sipio, Riccardo Rubei, Davide Di Ruscio, and Massimiliano Di Penta 2024. GPTSniffer: A CodeBERT-based classifier to detect source code written by ChatGPT Journal of Systems and Software, 112059. Replication package

  • Phoung T. Nguyen, Juri Di Rocco, Claudio Di Sipio, Mudita Shakya, Davide Di Ruscio, and Massimiliano Di Penta 2024. Automatic Categorization of GitHub Actions with Transformers and Few-shot Learning In Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM '24). Association for Computing Machinery, New York, NY, USA, 608–612. Replication package

  • Claudio Di Sipio, Riccardo Rubei, Juri Di Rocco, Davide Di Ruscio, and Ludovico Iovino 2024. On the Use of LLMs to Support the Development of Domain-Specific Modeling Languages. In Proceedings of the ACM/IEEE 27th International Conference on Model Driven Engineering Languages and Systems (MODELS Companion '24), Association for Computing Machinery, New York, NY, USA, 596–601. Replication package

  • Juri Di Rocco, Phoung T. Nguyen, Claudio Di Sipio, Riccardo Rubei, Davide Di Ruscio, and Massimiliano Di Penta 2024. DeepMig: A Transformer-based Approach to Support Coupled Library and Code Migrations Information and Software Technology, Volume 177, 2024, 107588, ISSN 0950-5849. Replication package

  • Antonio Della Porta, Vincenzo De Martino, Gilberto Recupito, Carmine Iemmino, Gemma Catolino, Dario Di Nucci, and Fabio Palomba 2024. Using Large Language Models to Support Software Engineering Documentation in Waterfall Life Cycles: Are We There Yet? in Proceedings of the 4th CINI National Congress on Artificial Intelligence.

  • Gianmario Voria, Giulia Sellitto, Carmine Ferrara, Francesco Abate, Andrea De Lucia, Filomena Ferrucci, Gemma Catolino, and Fabio Palomba 2024. Fairness-Aware Practices from Developers' Perspective: A Survey. Available at SSRN 4949224.

  • Gianmario Voria, Giulia Sellitto, Carmine Ferrara, Francesco Abate, Andrea De Lucia, Filomena Ferrucci, Gemma Catolino, Fabio Palomba 2024. A Catalog of Fairness-Aware Practices in Machine Learning Engineering ArXiv preprint arXiv:2408.16683.

  • Vincenzo De Martino, Gianmario Voria, Ciro Troiano, Gemma Catolino and Fabio Palomba 2024. Examining the Impact of Bias Mitigation Algorithms on the Sustainability of Ml-Enabled Systems: A Benchmark Study Available at SSRN 4966447.

Project leaders

Fabio Palomba

Assistant Professor

University of Salerno

Andrea Di Sorbo

Assistant Professor

University of Sannio

Davide Di Ruscio

Full professor

University of L'Aquila

Collaborators

Antinisca Di Marco

Associate professor

University of L'Aquila

Maria Tortorella

Associate Professor

University of Sannio

Giammaria Giordano

Post-doc

University of Salerno

Giordano d'Aloisio

Post-doc

University of L'Aquila

Arnaldo Sgueglia

Post-doc

University of Sannio

Claudio Di Sipio

Post-doc

University of L'Aquila

Gianmario Voria

PhD Student

University of Salerno

Viviana Pentangelo

PhD Student

University of Salerno

Vincenzo De Martino

PhD Student

University of Salerno

Francesco Casillo

PhD Student

University of Salerno