Gabriele Dominici

Gabriele Dominici

PhD Student
Università della Svizzera italiana
Gabriele Dominici is a PhD student at the Faculty of Informatics, Università della Svizzera italiana (USI). He works on developing interpretable machine-learning models that can generate counterfactuals, with the aim of improving the interaction between machines and humans.
Publications
Dario Fenoglio, Arianna Casanova, Francesco De Santis, Mohan Li, Gabriele Dominici, Johannes Schneider, Martin Gjoreski, Marc Langheinrich, Pietro Barbiero, Giovanni de Felice (2026). Federated Concept-Based Models: Interpretable models with distributed supervision. CoRR.
URL DOI
Francesco Sovrano, Gabriele Dominici, Alberto Bacchelli (2026). Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering. CoRR.
URL DOI
Francesco Sovrano, Gabriele Dominici, Alberto Bacchelli (2026). Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering. Proc. ACM Softw. Eng..
URL DOI
Francesco Sovrano, Gabriele Dominici, Marc Langheinrich (2026). Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation. Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, KDD 2026, Jeju Island, Korea, August 9-13, 2026.
URL DOI
Francesco Sovrano, Gabriele Dominici, Marc Langheinrich (2026). Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation. CoRR.
URL DOI
Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero, Zohreh Shams, Mateja Jamnik (2025). Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts. Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025.
URL
Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero, Zohreh Shams, Mateja Jamnik (2025). Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts. CoRR.
URL DOI
Gabriele Dominici, Pietro Barbiero, Mateo Espinosa Zarlenga, Alberto Termine, Martin Gjoreski, Giuseppe Marra, Marc Langheinrich (2025). Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning. The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025.
URL
Gabriele Dominici, Pietro Barbiero, Francesco Giannini, Martin Gjoreski, Giuseppe Marra, Marc Langheinrich (2025). Counterfactual Concept Bottleneck Models. The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025.
URL
Andrea Pugnana, Riccardo Massidda, Francesco Giannini, Pietro Barbiero, Mateo Espinosa Zarlenga, Roberto Pellungrini, Gabriele Dominici, Fosca Giannotti, Davide Bacciu (2025). Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts. Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diego, CA, USA, December 2-7, 2025 / Mexico City, Mexico, November 30 - December 5, 2025.
URL
Andrea Pugnana, Riccardo Massidda, Francesco Giannini, Pietro Barbiero, Mateo Espinosa Zarlenga, Roberto Pellungrini, Gabriele Dominici, Fosca Giannotti, Davide Bacciu (2025). Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts. CoRR.
URL DOI
David Debot, Pietro Barbiero, Gabriele Dominici, Giuseppe Marra (2025). Interpretable Hierarchical Concept Reasoning through Attention-Guided Graph Learning. CoRR.
URL DOI
Francesco Sovrano, Gabriele Dominici, Rita Sevastjanova, Alessandra Stramiglio, Alberto Bacchelli (2025). Is General-Purpose AI Reasoning Sensitive to Data-Induced Cognitive Biases? Dynamic Benchmarking on Typical Software Engineering Dilemmas. CoRR.
URL DOI
Teague McMillan, Gabriele Dominici, Martin Gjoreski, Marc Langheinrich (2025). Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?. CoRR.
URL DOI
Gabriele Dominici, Pietro Barbiero, Francesco Giannini, Martin Gjoreski, Marc Langheinrich (2024). AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model. Joint Proceedings of the xAI 2024 Late-breaking Work, Demos and Doctoral Consortium co-located with the 2nd World Conference on eXplainable Artificial Intelligence (xAI-2024), Valletta, Malta, July 17-19, 2024.
PDF
Gabriele Dominici, Pietro Barbiero, Francesco Giannini, Martin Gjoreski, Marc Langheinrich (2024). AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model. CoRR.
URL DOI
Gabriele Dominici, Pietro Barbiero, Mateo Espinosa Zarlenga, Alberto Termine, Martin Gjoreski, Giuseppe Marra, Marc Langheinrich (2024). Causal Concept Embedding Models: Beyond Causal Opacity in Deep Learning. CoRR.
URL DOI
Gabriele Dominici, Pietro Barbiero, Francesco Giannini, Martin Gjoreski, Giuseppe Marra, Marc Langheinrich (2024). Climbing the Ladder of Interpretability with Counterfactual Concept Bottleneck Models. CoRR.
URL DOI
Nursena Köprücü, Meher Shashwat Nigam, Shicheng Xu, Biruk Abere, Gabriele Dominici, Andrew Rodriguez, Sharvaree Vadgama, Berfin Inal, Alberto Tono (2024). DC3DO: Diffusion Classifier for 3D Objects. CoRR.
URL DOI
Francesco Bombassei De Bona, Gabriele Dominici, Tim Miller, Marc Langheinrich, Martin Gjoreski (2024). Evaluating Explanations Through LLMs: Beyond Traditional User Studies. CoRR.
URL DOI
Dario Fenoglio, Gabriele Dominici, Pietro Barbiero, Alberto Tonda, Martin Gjoreski, Marc Langheinrich (2024). Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning. Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024.
URL
Dario Fenoglio, Gabriele Dominici, Pietro Barbiero, Alberto Tonda, Martin Gjoreski, Marc Langheinrich (2024). Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning. CoRR.
URL DOI
Gabriele Dominici, Pietro Barbiero, Lucie Charlotte Magister, Pietro Liò, Nikola Simidjievski (2023). SHARCS: Shared Concept Space for Explainable Multimodal Learning. CoRR.
URL DOI