2 citations · 3 across the 14 of their papers we have counts for
18 papers
Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety
Fazl Barez, Tung-Yu Wu, Hunar Batra +24
Neural networks are likely to be among the most consequential artefacts in human history. As these systems become more capable and autonomous, their potential to cause societal har…
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation
Gabriele Dominici, Teague McMillan, Fazl Barez +2
Chain-of-thought (CoT) prompting elicits step-by-step rationales that appear to explain model predictions, but there is no guarantee these steps causally drive the final answer. In…
Distributed Subliminal Learning: Replacing Model Updates with Random-Carrier Outputs
Dario Fenoglio, Gabriele Dominici, Martin Gjoreski +1
Collaborative learning typically exchanges model parameters: federated clients communicate updates, while independently adapted foundation models are combined by exchanging adapter…
Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation
Francesco Sovrano, Gabriele Dominici, Marc Langheinrich
A central goal of explainable AI is to express large language model (LLM) decision logic symbolically and ground it in internal mechanisms. Existing rule-extraction methods usually…
Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering
Francesco Sovrano, Gabriele Dominici, Alberto Bacchelli
Prompt-induced cognitive biases are changes in a general-purpose AI (GPAI) system's decisions caused solely by biased wording in the input (e.g., framing, anchors), not task logic.…
Federated Concept-Based Models: Interpretable models with distributed supervision
Dario Fenoglio, Arianna Casanova, Francesco De Santis +6
Concept-based Models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept annotations are costly and rarely a…
Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?
Teague McMillan, Gabriele Dominici, Martin Gjoreski +1
Large Language Models (LLMs) often produce explanations that do not faithfully reflect the factors driving their predictions. In healthcare settings, such unfaithfulness is especia…
Is General-Purpose AI Reasoning Sensitive to Data-Induced Cognitive Biases? Dynamic Benchmarking on Typical Software Engineering Dilemmas
Francesco Sovrano, Gabriele Dominici, Rita Sevastjanova +2
Human cognitive biases in software engineering can lead to costly errors. While general-purpose AI (GPAI) systems may help mitigate these biases due to their non-human nature, thei…
Interpretable Hierarchical Concept Reasoning through Attention-Guided Graph Learning
David Debot, Pietro Barbiero, Gabriele Dominici +1
Concept-Based Models (CBMs) are a class of deep learning models that provide interpretability by explaining predictions through high-level concepts. These models first predict conc…
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero +2
In this paper, we investigate how concept-based models (CMs) respond to out-of-distribution (OOD) inputs. CMs are interpretable neural architectures that first predict a set of hig…
Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
Andrea Pugnana, Riccardo Massidda, Francesco Giannini +6
Concept Bottleneck Models (CBMs) are machine learning models that improve interpretability by grounding their predictions on human-understandable concepts, allowing for targeted in…
Evaluating Explanations Through LLMs: Beyond Traditional User Studies
Francesco Bombassei De Bona, Gabriele Dominici, Tim Miller +2
As AI becomes fundamental in sectors like healthcare, explainable AI (XAI) tools are essential for trust and transparency. However, traditional user studies used to evaluate these…
DC3DO: Diffusion Classifier for 3D Objects
Nursena Koprucu, Meher Shashwat Nigam, Shicheng Xu +6
Inspired by Geoffrey Hinton emphasis on generative modeling, To recognize shapes, first learn to generate them, we explore the use of 3D diffusion models for object classification.…
AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model
Gabriele Dominici, Pietro Barbiero, Francesco Giannini +2
Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users. Among these techniqes, Concept Bottleneck Mo…
Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
Gabriele Dominici, Pietro Barbiero, Mateo Espinosa Zarlenga +4
Causal opacity denotes the difficulty in understanding the "hidden" causal structure underlying the decisions of deep neural network (DNN) models. This leads to the inability to re…
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
Dario Fenoglio, Gabriele Dominici, Pietro Barbiero +3
Federated Learning (FL), a privacy-aware approach in distributed deep learning environments, enables many clients to collaboratively train a model without sharing sensitive data, t…
Counterfactual Concept Bottleneck Models
Gabriele Dominici, Pietro Barbiero, Francesco Giannini +3
Current deep learning models are not designed to simultaneously address three fundamental questions: predict class labels to solve a given classification task (the "What?"), simula…
SHARCS: Shared Concept Space for Explainable Multimodal Learning
Gabriele Dominici, Pietro Barbiero, Lucie Charlotte Magister +2
Multimodal learning is an essential paradigm for addressing complex real-world problems, where individual data modalities are typically insufficient to accurately solve a given mod…