36 citations · 46 across the 21 of their papers we have counts for
24 papers
Harmful Partial Interventions and Benign Leakage in Concept-based Models
Gregory Verghese, Christopher J. Soelistyo, Mateo Espinosa Zarlenga +2
Artificial intelligence systems deployed in high-risk settings increasingly require models that support meaningful human oversight. Concept-based models (CMs) offer a promising fra…
Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations
Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik
Sparse autoencoders (SAEs) decompose language model activations into sparse features, yet these models traditionally encode each token independently, failing to expose information…
In Defense of Information Leakage in Concept-based Models
Mateo Espinosa Zarlenga
Concept-based models (CMs), deep neural networks that ground their predictions on representations aligned with human-understandable concepts (e.g., "round", "stripes", etc.), have…
The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics
Pietro Barbiero, Giovanni De Felice, Mateo Espinosa Zarlenga +5
As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations. However, i…
CB-SLICE: Concept-Based Interpretable Error Slice Discovery
Yael Konforti, Mateo Espinosa Zarlenga, Elaf Almahmoud +1
Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Identifying these groups and the…
Don't Lose Focus: Activation Steering via Key-Orthogonal Projections
Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik
Activation steering controls LLM behaviour towards target behaviour by intervening in internal representations, yet it often degrades reasoning and retrieval performance. We argue…
Digging Deeper: Learning Multi-Level Concept Hierarchies
Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik
Although concept-based models promise interpretability by explaining predictions with human-understandable concepts, they typically rely on exhaustive annotations and treat concept…
Hierarchical Concept-based Interpretable Models
Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik
Modern deep neural networks remain challenging to interpret due to the opacity of their latent representations, impeding model understanding, debugging, and debiasing. Concept Embe…
Mixture of Concept Bottleneck Experts
Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice +7
Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically constrain their task predictor…
Actionable Interpretability Must Be Defined in Terms of Symmetries
Pietro Barbiero, Mateo Espinosa Zarlenga, Francesco Giannini +4
This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpr…
Foundations of Interpretable Models
Pietro Barbiero, Mateo Espinosa Zarlenga, Alberto Termine +2
We argue that existing definitions of interpretability are not actionable in that they fail to inform users about general, sound, and robust interpretable model design. This makes…
Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
Emiliano Penaloza, Tianyue H. Zhang, Laurent Charlin +1
Concept Bottleneck Models (CBMs) propose to enhance the trustworthiness of AI systems by constraining their decisions on a set of human-understandable concepts. However, CBMs typic…
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…
Neural Interpretable Reasoning
Pietro Barbiero, Giuseppe Marra, Gabriele Ciravegna +5
We formalize a novel modeling framework for achieving interpretability in deep learning, anchored in the principle of inference equivariance. While the direct verification of inter…
Efficient Bias Mitigation Without Privileged Information
Mateo Espinosa Zarlenga, Swami Sankaranarayanan, Jerone T. A. Andrews +3
Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously…
Understanding Inter-Concept Relationships in Concept-Based Models
Naveen Raman, Mateo Espinosa Zarlenga, Mateja Jamnik
Concept-based explainability methods provide insight into deep learning systems by constructing explanations using human-understandable concepts. While the literature on human reas…
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…
Do Concept Bottleneck Models Respect Localities?
Naveen Raman, Mateo Espinosa Zarlenga, Juyeon Heo +1
Concept-based explainability methods use human-understandable intermediaries to produce explanations for machine learning models. These methods assume concept predictions can help…
Learning to Receive Help: Intervention-Aware Concept Embedding Models
Mateo Espinosa Zarlenga, Katherine M. Collins, Krishnamurthy Dvijotham +3
Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property…
Interpretable Neural-Symbolic Concept Reasoning
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini +7
Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning…
Human Uncertainty in Concept-Based AI Systems
Katherine M. Collins, Matthew Barker, Mateo Espinosa Zarlenga +6
Placing a human in the loop may abate the risks of deploying AI systems in safety-critical settings (e.g., a clinician working with a medical AI system). However, mitigating risks…
Towards Robust Metrics for Concept Representation Evaluation
Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams +4
Recent work on interpretability has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as conc…
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna +9
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworth…