8 citations · 21 across the 17 of their papers we have counts for
20 papers
When Are Concept Bottleneck Model Explanations Faithful and Compact?
Stefano Teso, Emanuele Marconato, Steve Azzolin +1
Concept bottleneck models (CBMs) are neural classifiers that allow to explain their decisions via high-level concepts, potentially enabling understanding, steering and debugging. H…
Are Concept Bottleneck Models Effective as Decision-Support Systems?
Alessandro Bogani, Nicola Debole, Emanuele Marconato +3
Concept Bottleneck Models (CBMs) are interpretable-by-design neural networks that detect human-understandable concepts from the input and use them to generate predictions. By allow…
Relational Linear Properties in Language Models: An Empirical Investigation
Giovanni Valer, Luigi Gresele, Marco Bronzini +1
Linear properties are ubiquitous in the representations of language models; however, testing them experimentally remains a challenging task. This work focuses on relational lineari…
Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations
Nicola Debole, Andrea Passerini, Stefano Teso +2
Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the conc…
Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
Samuele Bortolotti, Emanuele Marconato, Andrea Pugnana +2
Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reliability in high-stakes applica…
Logit Distance Bounds Representational Similarity
Beatrix M. G. Nielsen, Emanuele Marconato, Luigi Gresele +2
For a broad family of discriminative models that includes autoregressive language models, identifiability results imply that if two models induce the same conditional distributions…
Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
Emanuele Marconato, Samuele Bortolotti, Emile van Krieken +6
Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding, e.g. safety or structural constraints. As such, it represents…
When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective
Beatrix M. G. Nielsen, Emanuele Marconato, Andrea Dittadi +1
When and why representations learned by different deep neural networks are similar is an active research topic. We choose to address these questions from the perspective of identif…
If Concept Bottlenecks are the Question, are Foundation Models the Answer?
Nicola Debole, Pietro Barbiero, Francesco Giannini +3
Concept Bottleneck Models (CBMs) are neural networks designed to conjoin high performance with ante-hoc interpretability. CBMs work by first mapping inputs (e.g., images) to high-l…
Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
Samuele Bortolotti, Emanuele Marconato, Paolo Morettin +2
Concept-based Models are neural networks that learn a concept extractor to map inputs to high-level concepts and an inference layer to translate these into predictions. Ensuring th…
All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
Emanuele Marconato, Sébastien Lachapelle, Sebastian Weichwald +1
We analyze identifiability as a possible explanation for the ubiquity of linear properties across language models, such as the vector difference between the representations of "eas…
A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
Samuele Bortolotti, Emanuele Marconato, Tommaso Carraro +5
The advent of powerful neural classifiers has increased interest in problems that require both learning and reasoning. These problems are critical for understanding important prope…
BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
Emanuele Marconato, Samuele Bortolotti, Emile van Krieken +3
Neuro-Symbolic (NeSy) predictors that conform to symbolic knowledge - encoding, e.g., safety constraints - can be affected by Reasoning Shortcuts (RSs): They learn concepts consist…
Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning
Emanuele Marconato, Andrea Passerini, Stefano Teso
Focus in Explainable AI is shifting from explanations defined in terms of low-level elements, such as input features, to explanations encoded in terms of interpretable concepts lea…
Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts
Emanuele Marconato, Stefano Teso, Antonio Vergari +1
Neuro-Symbolic (NeSy) predictive models hold the promise of improved compliance with given constraints, systematic generalization, and interpretability, as they allow to infer labe…
Neuro-Symbolic Reasoning Shortcuts: Mitigation Strategies and their Limitations
Emanuele Marconato, Stefano Teso, Andrea Passerini
Neuro-symbolic predictors learn a mapping from sub-symbolic inputs to higher-level concepts and then carry out (probabilistic) logical inference on this intermediate representation…
Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal
Emanuele Marconato, Gianpaolo Bontempo, Elisa Ficarra +3
We introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence of neuro-symbolic tasks, that is, it has to map sub-symbolic inputs to high-level concepts and…
GlanceNets: Interpretabile, Leak-proof Concept-based Models
Emanuele Marconato, Andrea Passerini, Stefano Teso
There is growing interest in concept-based models (CBMs) that combine high-performance and interpretability by acquiring and reasoning with a vocabulary of high-level concepts. A k…
Response to a comment on "Vindication of entanglement-based witnesses in hybrid quantum systems"
Chiara Marletto, Emanuele Marconato
In a recent paper, we vindicated a general entanglement-based witness of non-classicality in hybrid quantum systems. Our vindication refutes a counterexample to the witness, propos…
Vindication of entanglement-based witnesses of non-classicality in hybrid systems
Emanuele Marconato, Chiara Marletto
Recently, Vedral and one of us proposed an entanglement-based witness of non-classicality in systems that need not obey quantum theory, based on constructor-information-theoretic i…