Cover Image

Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bortolotti, Samuele, Marconato, Emanuele, Morettin, Paolo, Passerini, Andrea, Teso, Stefano
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
by: Bortolotti, Samuele, et al.
Published: (2024)

Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
by: Bortolotti, Samuele, et al.
Published: (2026)

BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
by: Marconato, Emanuele, et al.
Published: (2024)

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
by: Marconato, Emanuele, et al.
Published: (2025)

Probabilistic ML Verification via Weighted Model Integration
by: Morettin, Paolo, et al.
Published: (2024)

Logically Consistent Language Models via Neuro-Symbolic Integration
by: Calanzone, Diego, et al.
Published: (2024)

If Concept Bottlenecks are the Question, are Foundation Models the Answer?
by: Debole, Nicola, et al.
Published: (2025)

Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
by: Azzolin, Steve, et al.
Published: (2024)

Personalized Algorithmic Recourse with Preference Elicitation
by: De Toni, Giovanni, et al.
Published: (2022)

GNN Explanations that do not Explain and How to find Them
by: Azzolin, Steve, et al.
Published: (2026)

When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective
by: Nielsen, Beatrix M. G., et al.
Published: (2025)

Semantic Loss Functions for Neuro-Symbolic Structured Prediction
by: Ahmed, Kareem, et al.
Published: (2024)

All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
by: Marconato, Emanuele, et al.
Published: (2024)

Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations
by: Debole, Nicola, et al.
Published: (2026)

GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
by: Shindo, Hikaru, et al.
Published: (2026)

A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfaction
by: Kurscheidt, Leander, et al.
Published: (2025)

Neuro-Symbolic Concepts
by: Mao, Jiayuan, et al.
Published: (2025)

The KANDY Benchmark: Incremental Neuro-Symbolic Learning and Reasoning with Kandinsky Patterns
by: Lorello, Luca Salvatore, et al.
Published: (2024)

Neuro-Symbolic Rule Lists
by: Xu, Sascha, et al.
Published: (2024)

Learning To Guide Human Decision Makers With Vision-Language Models
by: Banerjee, Debodeep, et al.
Published: (2024)

The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning
by: Cunnington, Daniel, et al.
Published: (2024)

Enhancing SMT-based Weighted Model Integration by Structure Awareness
by: Spallitta, Giuseppe, et al.
Published: (2023)

Logit Distance Bounds Representational Similarity
by: Nielsen, Beatrix M. G., et al.
Published: (2026)

Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
by: Bronzini, Marco, et al.
Published: (2025)

ConceptLens: from Pixels to Understanding
by: Dalal, Abhilekha, et al.
Published: (2024)

A Learnability Analysis on Neuro-Symbolic Learning
by: He, Hao-Yuan, et al.
Published: (2025)

Softened Symbol Grounding for Neuro-symbolic Systems
by: Li, Zenan, et al.
Published: (2024)

Explainable Diagnosis Prediction through Neuro-Symbolic Integration
by: Lu, Qiuhao, et al.
Published: (2024)

Neuro-Symbolic AI: Explainability, Challenges, and Future Trends
by: Zhang, Xin, et al.
Published: (2024)

Bridging the Gap: Representation Spaces in Neuro-Symbolic AI
by: Zhang, Xin, et al.
Published: (2024)

Simple and Effective Transfer Learning for Neuro-Symbolic Integration
by: Daniele, Alessandro, et al.
Published: (2024)

Neuro-Symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation
by: Christopher, Jacob K., et al.
Published: (2025)

Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints
by: Scassola, Davide, et al.
Published: (2023)

Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning
by: Keller, Leon, et al.
Published: (2025)

Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection
by: Hu, Wen-Chao, et al.
Published: (2024)

A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
by: Cotnareanu, Joseph, et al.
Published: (2026)

Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees
by: Tao, Lue, et al.
Published: (2023)

GPT-2 Through the Lens of Vector Symbolic Architectures
by: Knittel, Johannes, et al.
Published: (2024)

Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
by: Yang, Xiao-Wen, et al.
Published: (2025)

Neuro-Symbolic Decoding of Neural Activity
by: Wang, Yanchen, et al.
Published: (2026)