36 citations · 46 across the 21 of their papers we have counts for
10 papers · 1 filter
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…