Gabriele Dominici |https://pc.inf.usi.ch/people/gabriele-dominici/Gabriele DominiciHugoBlox Kit (https://hugoblox.com)en-usThu, 01 Jan 2026 00:00:00 +0000https://pc.inf.usi.ch/media/people/gabriele-dominici_hu_a80763ee0547d93d.jpgGabriele Dominicihttps://pc.inf.usi.ch/people/gabriele-dominici/Federated Concept-Based Models: Interpretable models with distributed supervisionhttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2602-04093/Thu, 01 Jan 2026 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2602-04093/Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineeringhttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2604-16756/Thu, 01 Jan 2026 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2604-16756/Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablationhttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2605-03058/Thu, 01 Jan 2026 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2605-03058/Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shiftshttps://pc.inf.usi.ch/publications/dblp-conficml-zarlenga-dbsj-25/Wed, 01 Jan 2025 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-conficml-zarlenga-dbsj-25/Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shiftshttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2504-17921/Wed, 01 Jan 2025 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2504-17921/Causal Concept Graph Models: Beyond Causal Opacity in Deep Learninghttps://pc.inf.usi.ch/publications/dblp-conficlr-dominici-bztgml-25/Wed, 01 Jan 2025 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-conficlr-dominici-bztgml-25/Counterfactual Concept Bottleneck Modelshttps://pc.inf.usi.ch/publications/dblp-conficlr-dominici-bggml-25/Wed, 01 Jan 2025 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-conficlr-dominici-bggml-25/Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Expertshttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2503-16199/Wed, 01 Jan 2025 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2503-16199/Interpretable Hierarchical Concept Reasoning through Attention-Guided Graph Learninghttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2506-21102/Wed, 01 Jan 2025 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2506-21102/Is General-Purpose AI Reasoning Sensitive to Data-Induced Cognitive Biases? Dynamic Benchmarking on Typical Software Engineering Dilemmashttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2508-11278/Wed, 01 Jan 2025 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2508-11278/Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2510-24236/Wed, 01 Jan 2025 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2510-24236/AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Modelhttps://pc.inf.usi.ch/publications/dblp-confxai-dominici-bggl-24/Mon, 01 Jan 2024 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-confxai-dominici-bggl-24/AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Modelhttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2405-16508/Mon, 01 Jan 2024 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2405-16508/Causal Concept Embedding Models: Beyond Causal Opacity in Deep Learninghttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2405-16507/Mon, 01 Jan 2024 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2405-16507/Climbing the Ladder of Interpretability with Counterfactual Concept Bottleneck Modelshttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2402-01408/Mon, 01 Jan 2024 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2402-01408/DC3DO: Diffusion Classifier for 3D Objectshttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2408-06693/Mon, 01 Jan 2024 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2408-06693/Evaluating Explanations Through LLMs: Beyond Traditional User Studieshttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2410-17781/Mon, 01 Jan 2024 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2410-17781/Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learninghttps://pc.inf.usi.ch/publications/dblp-confnips-fenoglio-dbtgl-24/Mon, 01 Jan 2024 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-confnips-fenoglio-dbtgl-24/Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learninghttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2405-15632/Mon, 01 Jan 2024 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2405-15632/SHARCS: Shared Concept Space for Explainable Multimodal Learninghttps://pc.inf.usi.ch/publications/dblp-journalscorrabs-2307-00316/Sun, 01 Jan 2023 00:00:00 +0000https://pc.inf.usi.ch/publications/dblp-journalscorrabs-2307-00316/