It takes two to tango: a synergistic approach to human-machine decision making

Livrables

Brand and comm. channels

Brand and communications channelsestablished and live.

First data management plan

(First) Ethical, Gender, Legal, Security Compliance Framework for the data management lifecycle.

Second data management plan

(Second) Ethical, Gender, Legal, Security Compliance Framework for the data management lifecycle

Cognition-aware explanations for HML

Definition, design and development ofcognitive-aware explanations.

First exploitation strategy

First exploitation strategy and roadmap to market

Cognition-aware explanations for DM

Definition, design and development of theunified explanation-driven HDM process

First communication and dissemination report

Periodic report on C&D activities

Application guidelines

Document with guidelines for theimplementation and coordination of theapplications.

TANGO system specifications

Architectural specifications of the TANGObackend system.

Publications

A Causal Framework for Evaluating Deferring Systems

Auteurs: Filippo Palomba, Andrea Pugnana, Jose Manuel Alvarez, Salvatore Ruggieri
Éditeur: PMLR

Towards Logically Consistent Language Models via Probabilistic Reasoning

Auteurs: Calanzone, Diego; Teso, Stefano; Vergari, Antonio
Publié dans: 2024
Éditeur: ICLR 2024 Workshop on Reliable and Responsible Foundation Models
DOI: 10.48550/ARXIV.2404.12843

A Simple and Expressive Graph Neural Network Based Method for Structural Link Representation

Auteurs: Veronica Lachi, Francesco Ferrini, Antonio Longa, Bruno Lepri, Andrea Passerini
Publié dans: Proceedings of the GRaM Workshop at ICML 2024, 2024
Éditeur: PMLR

Uncertainty Matters: Stable Conclusions Under Unstable Assessment of Fairness Results

Auteurs: Ainhize Barrainkua, Paula Gordaliza, Jose A Lozano, Novi Quadrianto
Publié dans: Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS) 2024, Valencia, Spain. PMLR., 2024
Éditeur: Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS) 2024, Valencia, Spain. PMLR: Volume 238.

Learning to Intervene on Concept Bottlenecks

Auteurs: David Steinmann, Wolfgang Stammer, Felix Friedrich, Kristian Kersting
Publié dans: Proceedings of ICML, 2024
Éditeur: ICML

Ensemble Counterfactual Explanations for Churn Analysis

Auteurs: Samuele Tonati, Marzio Di Vece, Roberto Pellungrini, Fosca Giannotti
Publié dans: Lecture Notes in Computer Science, Discovery Science, 2025
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-78980-9_21

Preference Elicitation in Interactive and User-centered Algorithmic Recourse: an Initial Exploration

Auteurs: Seyedehdelaram Esfahani, Giovanni De Toni, Bruno Lepri, Andrea Passerini, Katya Tentori, Massimo Zancanaro
Publié dans: Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, 2024
Éditeur: ACM
DOI: 10.1145/3627043.3659556

PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning

Auteurs: Luca Corbucci, Mikko A. Heikkilä, David Solans Noguero, Anna Monreale, Nicolas Kourtellis
Publié dans: Frontiers in Artificial Intelligence and Applications, ECAI 2024, 2024
Éditeur: IOS Press
DOI: 10.3233/FAIA240671

Pix2Code: Learning to Compose Neural Visual Concepts as Programs

Auteurs: Antonia Wüst, Wolfgang Stammer, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting
Publié dans: Proceedings of UAI, 2024
Éditeur: UAI

L2loRe: a method for explaining the reject option

Auteurs: Clara Punzi, Roberto Pellungrini, Fosca Giannotti
Éditeur: Discovery Science 2024

Systems with Switching Causal Relations: A Meta-Causal Perspective

Auteurs: Moritz Willig, Tim Tobiasch, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami, Kristian Kersting
Publié dans: Proceedings of ICLR, 2025
Éditeur: International Conference on Learning Representations (ICLR)

Sheaf Diffusion Goes Nonlinear: Enhancing GNNs with Adaptive Sheaf Laplacians

Auteurs: Olga Zaghen, Antonio Longa, Steve Azzolin, Lev Telyatnikov, Andrea Passerini, Pietro Lio
Publié dans: Proceedings of the GRaM Workshop at ICML 2024, 2024
Éditeur: PMLR

Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph

Auteurs: Marco Bronzini, Carlo Nicolini, Bruno Lepri, Jacopo Staiano, Andrea Passerini
Publié dans: Proceedings of COLM, 2024, 2024
Éditeur: openreview.net

Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs

Auteurs: Steve Azzolin, Antonio Longa, Stefano Teso, Andrea Passerini
Publié dans: Proceedings of ICLR, 2025
Éditeur: OpenReview

BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts

Auteurs: Marconato, Emanuele; Bortolotti, Samuele; van Krieken, Emile; Vergari, Antonio; Passerini, Andrea; Teso, Stefano
Publié dans: Proceedings of UAI, 2024
Éditeur: Proceedings of UAI, 2024

GLOR-FLEX: Local to Global Rule-Based EXplanations for Federated Learning

Auteurs: Rami Haffar; Francesca Naretto; David Sánchez; Anna Monreale; Josep Domingo-Ferrer
Publié dans: 2024 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Éditeur: IEEE
DOI: 10.5281/ZENODO.15310465

Epistemic Interaction – Tuning Interfaces to Provide Information for AI Support

Auteurs: Alan Dix, Ben Wilson Matt Roach, Tommaso Turchi, Alessio Malizia
Publié dans: SYNERGY 2024 – Designing and Building Hybrid Human-AI Systems 2024, 2024
Éditeur: SYNERGY 2024 – Designing and Building Hybrid Human-AI Systems 2024

Neural Concept Binder

Auteurs: Wolfgang Stammer, Antonia Wüst, David Steinmann, Kristian Kersting
Publié dans: Advances in Neural Information Processing, 2024
Éditeur: NeurIPS

One-Shot Clustering for Federated Learning

Auteurs: Maciej Krzysztof Zuziak, Roberto Pellungrini, Salvatore Rinzivillo
Publié dans: 2024 IEEE International Conference on Big Data (BigData), 2025
Éditeur: IEEE
DOI: 10.1109/BIGDATA62323.2024.10825763

Designing for situated AI-human decision making: Lessons learned from a primary care deployment

Auteurs: Ben Wilson, Darren Scott, Matt Roach, Emily Nielsen, Berndt Muller
Publié dans: SYNERGY 2024 – Designing and Building Hybrid Human-AI Systems 2024, 2024
Éditeur: SYNERGY 2024 – Designing and Building Hybrid Human-AI Systems 2024

SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks

Auteurs: Mátyás Vincze, Laura Ferrarotti, Leonardo Lucio Custode, Bruno Lepri, Giovanni Iacca
Publié dans: Proceedings of AAAI 2025
Éditeur: The Associations for the Advancement of Artificial Intelligence

Interpretable and Fair Mechanisms for Abstaining Classifiers

Auteurs: Daphne Lenders, Andrea Pugnana, Roberto Pellungrini, Toon Calders, Dino Pedreschi, Fosca Giannotti
Publié dans: Lecture Notes in Computer Science, Machine Learning and Knowledge Discovery in Databases. Research Track, 2024
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-70368-3_25

Enhancing Privacy and Utility in Federated Learning: A Hybrid P2P and Server-Based Approach with Differential Privacy Protection

Auteurs: Luca Corbucci, Anna Monreale, Roberto Pellungrini
Publié dans: Proceedings of the 21st International Conference on Security and Cryptography, 2024
Éditeur: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0012863600003767

Logically Consistent Language Models via Neuro-Symbolic Integration

Auteurs: Diego Calanzone, Stefano Teso, Antonio Vergari
Publié dans: International Conference on Learning Representations (ICLR), 2025

Disagreement-based Active Learning for Robustness Against Subpopulation Shifts

Auteurs: Yeat Jeng Ng, Viktoriia Sharmanska, Thomas Kehrenberg, Anastasia Pentina, Novi Quadrianto
Publié dans: Proceedings of the HLDM Workshop at ECML 2024, 2024
Éditeur: Proceedings of the HLDM Workshop @ ECML 2024

Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations

Auteurs: Nicolò Penzo, Maryam Sajedinia, Bruno Lepri, Sara Tonelli, and Marco Guerini
Publié dans: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Éditeur: Association for Computational Linguistics
DOI: 10.18653/V1/2024.EMNLP-MAIN.628

Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?

Auteurs: Antonia Wüst, Tim Tobiasch, Lukas Helff, Devendra Singh Dhami, Constantin A. Rothkopf, Kristian Kersting
Publié dans: Proceedings of Sys2-Reasoning Workshop @ NeurIPS 2024
Éditeur: NeurIPS Workshop

A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts

Auteurs: Bortolotti, Samuele; Marconato, Emanuele; Carraro, Tommaso; Morettin, Paolo; van Krieken, Emile; Vergari, Antonio; Teso, Stefano; Passerini, Andrea
Publié dans: Advances in Neural Information Processing Systems 37 (NeurIPS 2024), 2024
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain

Auteurs: Burcu Sayin, Pasquale Minervini, Jacopo Staiano, Andrea Passerini
Publié dans: Proceedings of the 6th Clinical Natural Language Processing Workshop, 2024
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2024.clinicalnlp-1.19

Coordination in dynamic interactions by converging on tacitly agreed joint plans

Auteurs: Arthur Le Pargneux, Hossam Zeitoun, Emmanouil Konstantinidis, Nick Chater
Publié dans: 2024
Éditeur: Center for Open Science
DOI: 10.31234/osf.io/w2x3f

A Frank System for Co-Evolutionary Hybrid Decision-Making

Auteurs: Federico Mazzoni, Riccardo Guidotti, Alessio Malizia
Publié dans: Lecture Notes in Computer Science, Advances in Intelligent Data Analysis XXII, 2024
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-58553-1_19

Systems with Switching Causal Relations: A Meta-Causal Perspective

Auteurs: Moritz Willig, Tim Tobiasch, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami, Kristian Kersting
Publié dans: Proceedings of CRL Workshop @ NeurIPS 2024
Éditeur: NeurIPS Workshop

Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents

Auteurs: Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, Kristian Kersting
Publié dans: Advances in Neural Information Processing, 2024
Éditeur: NeurIPS

Explainable AI in Time-Sensitive Scenarios: Prefetched Offline Explanation Model

Auteurs: Fabio Michele Russo, Carlo Metta, Anna Monreale, Salvatore Rinzivillo, Fabio Pinelli
Publié dans: Lecture Notes in Computer Science, Discovery Science, 2025
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-78980-9_11

Explaining the Explainers in Graph Neural Networks: a Comparative Study

Auteurs: Antonio Longa, Steve Azzolin, Gabriele Santin, Giulia Cencetti, Pietro Lio, Bruno Lepri, Andrea Passerini
Publié dans: ACM Computing Surveys, 2024, ISSN 0360-0300
Éditeur: Association for Computing Machinery (ACM)
DOI: 10.1145/3696444

CERN for AI: a theoretical framework for autonomous simulation-based artificial intelligence testing and alignment

Auteurs: Ljubiša Bojić; Matteo Cinelli; Dubravko Ćulibrk; Boris Delibašić
Publié dans: European Journal of Futures Research, 2024, ISSN 2195-2248
Éditeur: European Journal of Futures Research
DOI: 10.48550/ARXIV.2312.09402

Fostering effective hybrid human-LLM reasoning and decision making

Auteurs: Passerini, Andrea; Gema, Aryo; Minervini, Pasquale; Sayin, Burcu; Tentori, Katya
Publié dans: FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2025, ISSN 2624-8212
Éditeur: Frontiers Media SA
DOI: 10.3389/frai.2024.1464690

NeST: The neuro-symbolic transpiler

Auteurs: Viktor Pfanschilling, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting
Publié dans: International Journal of Approximate Reasoning, Numéro 179, 2025, ISSN 0888-613X
Éditeur: Elsevier BV
DOI: 10.1016/J.IJAR.2025.109369

AI alignment: Assessing the global impact of recommender systems

Auteurs: Ljubisa Bojic
Publié dans: Futures, Numéro 160, 2024, ISSN 0016-3287
Éditeur: Elsevier BV
DOI: 10.1016/J.FUTURES.2024.103383

Conversational technology and reactions to withheld information

Auteurs: Nikolos Gurney, George Loewenstein, Nick Chater
Publié dans: PLOS ONE, Numéro 19, 2024, ISSN 1932-6203
Éditeur: Public Library of Science (PLoS)
DOI: 10.1371/journal.pone.0301382

Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fields

Auteurs: Francesco Spinnato, Riccardo Guidotti, Anna Monreale, Mirco Nanni
Publié dans: IEEE Access, Numéro 12, 2024, ISSN 2169-3536
Éditeur: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/ACCESS.2024.3464743

Resource-rational contractualism: A triple theory of moral cognition

Auteurs: Sydney Levine, Nick Chater, Joshua B. Tenenbaum, Fiery Cushman
Publié dans: Behavioral and Brain Sciences, 2024, ISSN 0140-525X
Éditeur: Cambridge University Press (CUP)
DOI: 10.1017/S0140525X24001067

When rules are over-ruled: Virtual bargaining as a contractualist method of moral judgment

Auteurs: Sydney Levine, Max Kleiman-Weiner, Nick Chater, Fiery Cushman, Joshua B. Tenenbaum
Publié dans: Cognition, Numéro 250, 2024, ISSN 0010-0277
Éditeur: Elsevier BV
DOI: 10.1016/J.COGNITION.2024.105790

Rethinking and Recomputing the Value of Machine Learning Models

Auteurs: Burcu Sayin; Jie Yang; Xinyue Chen; Andrea Passerini; Fabio Casati
Publié dans: Crossref, 2024, ISSN 1573-7462
Éditeur: Artificial Intelligence Review
DOI: 10.21203/RS.3.RS-4833578/V1

Generative Model for Decision Trees

Auteurs: Riccardo Guidotti; Anna Monreale; Mattia Setzu; Giulia Volpi
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, 2024, ISSN 2374-3468
Éditeur: Proceedings of the AAAI Conference on Artificial Intelligence
DOI: 10.1609/AAAI.V38I19.30104

Beyond the Face: Biometrics and Society

Auteurs: Bojan, Perkov; Jelena, Adamović; Duje, Kozomara; Mila, Bajić; Duje, Prkut
Publié dans: 2023
Éditeur: SHARE Foundation
DOI: 10.5281/ZENODO.13819768

Livrables

Publications

Partager cette page Partager cette page sur les réseaux sociaux

Télécharger Télécharger le contenu de la page