Value-Aware Artificial Intelligence

Informazioni relative al progetto

VALAWAI

ID dell’accordo di sovvenzione: 101070930

DOI

10.3030/101070930

Data della firma CE 2 Novembre 2022

Data di avvio 1 Ottobre 2022

Data di completamento 30 Settembre 2026

Finanziato da

• The European Innovation Council (EIC)

Costo totale

€ 3 926 432,51

Contributo UE

€ 3 926 432,26

Coordinato da

AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS
Spain

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (9)

Integrative Model of Moral Cognition for AI

White paper bringing state of the art social psychology into the project

Value-aware medical protocols: use case setup

Use case detailed description along with plans on the support to valueaware protocols

Social robots and value-aware AI v1

Report on user studies on perception of value-aware AI, trust and evaluation in complex real world scenarios.

Results of the behavioral testing

Report on the best strategies to support human perception of AI systems as moral agents.

Quantitative measures for Value-Aware AI

Scientific paper proposing and motivating the measures published in high profile journal

Technical report and software components

Technical contributions (available as papers, open source software, documentation, and tutorials) validated in pilot studies.

Detection of markers of moral values in social media

Publication of the research presenting the scientific basis of morality detection and markers of misbehaviour.

Use cases and scenarios

Report on use cases and scenarios eliciting value-laden decisions for robots, design of study protocols.

Draft functional specification of the RGNW Toolbox and Moral Cognition Tool

Reporting on the initial functional specification of the RGNW Toolbox and Moral Cognition Tools

Other (4)

RGNW Toolbox and Moral Cognition Tools v1

Software toolbox and a report describing its release on open platforms as well as its adoption

Moral observatory platform and library

Release of internet platform and software library to visualise moral markers and their dynamics in social media.

Value-aware tools for the management of medical protocols v1

The releases of the components developed for the medical protocols domain.

RGNW Toolbox and Moral Cognition Tools v2

Software toolbox and a report describing its release on open platforms as well as its adoption.

Websites, patent fillings, videos etc. (1)

Project Website and Logo

Delivers the project website and logo

Pubblicazioni

Peer reviewed articles (18)

The role of political devotion in sharing partisan misinformation and resistance to fact-checking.

Autori: Clara Pretus, Camila Servin-Barthet, Elizabeth A. Harris, William J. Brady, Oscar Vilarroya, Jay J. Van Bavel
Pubblicato in: Journal of Experimental Psychology: General, Numero 152, 2024, ISSN 1939-2222
Editore: American Psychological Association (APA)
DOI: 10.1037/XGE0001436

Information Sciences

Autori: Marc Serramià, Maite López-Sánchez, Stefano Moretti, Juan A. Rodríguez-Aguilar
Pubblicato in: Information Sciences Journal, 2023, ISSN 0020-0255
Editore: ELSEVIER
DOI: 10.1016/j.ins.2023.02.063

Knowledge-Based Systems

Autori: Roger X. Lera-Leri; Enrico Liscio; Filippo Bistaffa; Catholijn M. Jonker; Maite Lopez-Sanchez; Pradeep K. Murukannaiah; Juan A. Rodriguez-Aguilar; Francisco Salas-Molina
Pubblicato in: Knowledge-Based Systems, 2024, ISSN 0950-7051
Editore: Elsevier BV
DOI: 10.1016/J.KNOSYS.2024.111453

Scientific Reports

Autori: Ziggy O'Reilly; Serena Marchesi; Agnieszka Wykowska
Pubblicato in: Scientific Reports, 2024, ISSN 2045-2322
Editore: Nature Publishing Group
DOI: 10.31234/OSF.IO/YBCDZ_V2

Encoding Ethics to Compute Value-Aligned Norms

Autori: Marc Serramia; Manel Rodriguez-Soto; Maite Lopez-Sanchez; Juan A. Rodriguez-Aguilar; Filippo Bistaffa; Paula Boddington; Michael Wooldridge; Carlos Ansotegui
Pubblicato in: Minds and Machines, 2023, ISSN 1572-8641
Editore: Springer Nature B.V.
DOI: 10.1007/S11023-023-09649-7

The AI4Citizen pilot: Pipelining AI-based technologies to support school-work alternation programmes

Autori: Athina Georgara, Raman Kazhamiakin, Ornella Mich, Alessio Palmero Aprosio, Jean-Christoph Pazzaglia, Juan Antonio Rodríguez Aguilar, Carles Sierra
Pubblicato in: Applied Intelligence, Numero 53, 2023, ISSN 0924-669X
Editore: Springer Science and Business Media LLC
DOI: 10.1007/S10489-023-04758-3

Combining theory of mind and abductive reasoning in agent-oriented programming

Autori: Nieves Montes, Michael Luck, Nardine Osman, Odinaldo Rodrigues, Carles Sierra
Pubblicato in: Autonomous Agents and Multi-Agent Systems, Numero 37, 2023, ISSN 1387-2532
Editore: Springer Science and Business Media LLC
DOI: 10.1007/S10458-023-09613-W

A computational model of Ostrom's Institutional Analysis and Development framework

Autori: Nieves Montes, Nardine Osman, & Carles Sierra
Pubblicato in: Artificial Intelligence, Numero 311, 2022, ISSN 0004-3702
Editore: Elsevier
DOI: 10.1016/j.artint.2022.103756

Is this a violation? Learning and understanding norm violations in online communities

Autori: Thiago Freitas dos Santos, Nardine Osman, Marco Schorlemmer
Pubblicato in: Artificial Intelligence, Numero 327, 2024, ISSN 0004-3702
Editore: Elsevier BV
DOI: 10.1016/J.ARTINT.2023.104058

Multi-objective reinforcement learning for designing ethical multi-agent environments.

Autori: Manel Rodríguez-Soto, Maite López-Sánchez, Juan A. Rodríguez-Aguilar
Pubblicato in: Neural Computing and Applications Journal, 2023, ISSN 1433-3058
Editore: Springer-Verlag
DOI: 10.1007/s00521-023-08898-y

International Journal of Social Robotics

Autori: Qiaoqiao Ren; Tony Belpaeme
Pubblicato in: International Journal of Social Robotics, 2024, ISSN 1875-4791
Editore: Springer Verlag
DOI: 10.48550/ARXIV.2411.12549

A multi-scenario approach to continuously learn and understand norm violations

Autori: Freitas dos Santos, Thiago; Osman, Nardine; Schorlemmer, Marco
Pubblicato in: Autonomous Agents and Multi-Agent Systems, 2023, ISSN 1573-7454
Editore: Springer Science+Business Media, LLC, part of Springer Nature
DOI: 10.1007/S10458-023-09619-4

Socio-Economic Planning Sciences

Autori: Francisco Salas-Molina, Filippo Bistaffa, Juan A. Rodríguez-Aguilar
Pubblicato in: Socio-Economic Planning Sciences, 2023, ISSN 0038-0121
Editore: Elsevier
DOI: 10.1016/j.seps.2023.101694

Information Sciences

Autori: Serramia, Marc; Lopez-Sanchez, Maite; Moretti, Stefano; Rodriguez-Aguilar, Juan A.
Pubblicato in: Information Sciences, 2023, ISSN 0020-0255
Editore: Elsevier BV
DOI: 10.1016/J.INS.2023.02.063

Emotion

Autori: Clara Pretus; Jillian K. Swencionis; Yifei Pei; Luis Marcos-Vidal; Ingrid J. Haas; William A. Cunningham; Dominic J. Packer; Jay J. Van Bavel
Pubblicato in: Emotion, 2023, ISSN 1528-3542
Editore: American Psychological Association
DOI: 10.31234/OSF.IO/ESBY8

Philosophical Transactions of the Royal Society B: Biological Sciences

Autori: Clara Pretus; Ali Javeed; Diána R Hughes; Kobi Hackenburg; Manos Tsakiris; Oscar Vilarroya; Jay Joseph Van Bavel
Pubblicato in: Philosophical Transactions of the Royal Society B: Biological Sciences, 2022, ISSN 0962-8436
Editore: Royal Society of London
DOI: 10.1098/RSTB.2023.0040

Understanding the sense of self through robotics

Autori: Tony J. Prescott, Kai Vogeley, Agnieszka Wykowska
Pubblicato in: Science Robotics, Numero 9, 2024, ISSN 2470-9476
Editore: American Association for the Advancement of Science (AAAS)
DOI: 10.1126/SCIROBOTICS.ADN2733

Online news ecosystem dynamics: supply, demand, diffusion, and the role of disinformation

Autori: Pietro Gravino; Giulio Prevedello; Emanuele Brugnoli
Pubblicato in: Applied Network Science, 2024, ISSN 2364-8228
Editore: Springer
DOI: 10.1007/S41109-024-00643-1

Other (4)

Moral agents as relational systems: The Contract-Based Model of Moral Cognition for AI

Autori: Luis Marcos Vidal, Serena Marchesi, Agnieszka Wykowska, Clara Pretus
Pubblicato in: 2024
Editore: Center for Open Science
DOI: 10.31234/OSF.IO/52X74

Modelling Moral Decision-Making in a Contractualist Artificial Agent

Autori: Giovanni Dalmasso, Luis Marcos Vidal, Clara Pretus
Pubblicato in: 2024
Editore: Center for Open Science
DOI: 10.31219/OSF.IO/658RS

Scaling crowdsourcing interventions to combat partisan misinformation

Autori: Clara Pretus; Helena Gil-Buitrago; Irene Cisma; Rosamunde C. Hendricks; Daniela Lizarazo-Villarreal
Pubblicato in: advances.in/psychology, 2024
Editore: Elsevier B.V.
DOI: 10.56296/AIP00018

A computational model of Ostrom's Institutional Analysis and Development framework

Autori: Montes, Nieves; Osman, Nardine; Sierra, Carles
Pubblicato in: Artificial Intelligence, 2022
Editore: Elsevier
DOI: 10.48550/ARXIV.2105.13151

Conference proceedings (17)

Fine-Grained Clustering of Social Media: How Moral Triggers Drive Preferences and Consensus

Autori: Emanuele Brugnoli, Pietro Gravino, Donald Ruggiero Lo Sardo, Vittorio Loreto, Giulio Prevedello
Pubblicato in: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, 2024
Editore: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0012595000003636

Moral Narratives of Robots Increase the Likelihood of Adopting the Intentional Stance

Autori: Ziggy O'Reilly, Serena Marchesi, Agnieszka Wykowska
Pubblicato in: Proceedings of the 12th International Conference on Human-Agent Interaction, 2025
Editore: ACM
DOI: 10.1145/3687272.3688312

Users' Perspectives on Value Awareness in Social Robots

Autori: Abbo, Giulio Antonio; Belpaeme, Tony
Pubblicato in: 2023
Editore: Association for Computing Machinery
DOI: 10.5281/zenodo.8123742

Towards Value Awareness in the Medical Field

Autori: Manel Rodriguez-Soto, Nardine Osman, Carles Sierra, Paula Sánchez Veja, Rocio Cintas Garcia, Cristina Farriols Danes, Montserrat Garcia Retortillo, Silvia Minguez Maso
Pubblicato in: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, 2024
Editore: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0012588600003636

A Computational Model of Ostrom's Institutional Analysis and Development Framework (Extended Abstract)

Autori: Nieves Montes, Nardine Osman, Carles Sierra
Pubblicato in: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
Editore: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/IJCAI.2023/786

MPG at DisCoTeX: Predicting Text Coherence by Tree-based Modelling of Linguistic Features

Autori: Martina Galletti, Pietro Gravino, Giulio Prevedello
Pubblicato in: Proceedings of the Eighth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2023), 2023, ISSN 1613-0073
Editore: CEUR-WS

Are Your Keywords Like My Queries? A Corpus-Wide Evaluation of Keyword Extractors with Real Searches

Autori: Martina Galletti, Giulio Prevedello, Emanuele Brugnoli, Donald Ruggiero Lo Sardo, Pietro Gravino
Pubblicato in: Proceedings of the 31st International Conference on Computational Linguistics, 2025
Editore: ACL Anthology

Towards a Definition of Awareness for Embodied AI

Autori: Giulio Abbo, Serena Marchesi, Kinga Ciupinska, Agnieszka Wykowska, Tony Belpaeme
Pubblicato in: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, 2024
Editore: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0012594800003636

Can Interpretability Layouts Influence Human Perception of Offensive Sentences?

Autori: Thiago Freitas dos Santos; Nardine Osman; Marco Schorlemmer
Pubblicato in: Lecture Notes in Computer Science ISBN: 9783031700736, 2024
Editore: Springer
DOI: 10.48550/ARXIV.2403.05581

Addressing the Value Alignment Problem Through Online Institutions

Autori: Pablo Noriega; Harko Verhagen; Julian Padget; Mark d’Inverno
Pubblicato in: Lecture Notes in Computer Science ISBN: 9783031491320, 2023
Editore: Springer
DOI: 10.1007/978-3-031-49133-7_5

Value Inference in Sociotechnical Systems

Autori: Enrico Liscio, Roger Lera Leri, Filippo Bistaffa, Roel I. J. Dobbe, Catholijn M. Jonker, Maite López Sánchez y Juan A. Rodríguez Aguilar, Pradeep K. Murukannaiah
Pubblicato in: Proceedings of the 22nd International Conference on Autonomous Agents and MultiAgent Systems (AAMAS '23), 2023
Editore: International Foundation for Autonomous Agents and Multiagent SystemsRichlandSC
DOI: 10.5555/3545946.3598838

"Awareness in robotics: An early perspective from the viewpoint of the EIC Pathfinder Challenge ""Awareness Inside"""

Autori: Della Santina, Cosimo; Hernandez Corbato, Carlos; Sisman, Burak; Leiva, Luis A.; Arapakis, Ioannis; Vakalellis, Michalis; Vanderdonckt, Jean
Pubblicato in: arXiv, Vol. 2402, no.1, p. 15 (2024), 2024
Editore: Springer Proceedings in Advanced Robotics
DOI: 10.1007/978-3-031-76424-0_20

An Agent-Based Model for Poverty and Discrimination Policy-Making

Autori: Montes, Nieves; Curto, Georgina; Osman, Nardine; Sierra, Carles
Pubblicato in: CUER WS, 2023, ISSN 1613-0073
Editore: CEUR workshop proceedings
DOI: 10.48550/arxiv.2303.13994

Notes on Measures for Information Access in Neuroscience and AI Systems

Autori: Giulio Prevedello, Luis Marcos-Vidal, Emanuele Brugnoli, Pietro Gravino
Pubblicato in: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, 2024
Editore: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0012596000003636

Cross-community Adapter Learning (CAL) to Understand the Evolving Meanings of Norm Violation

Autori: Thiago Freitas dos Santos, Stephen Cranefield, Bastin Tony Roy Savarimuthu, Nardine Osman, Marco Schorlemmer
Pubblicato in: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
Editore: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/IJCAI.2023/13

Assessing LLMs Responses in the Field of Domestic Sustainability: An Exploratory Study

Autori: Mathyas Giudici, Giulio Antonio Abbo, Ottavia Belotti, Alessio Braccini, Francesco Dubini, Riccardo Andrea Izzo, Pietro Crovari, Franca Garzotto
Pubblicato in: 2023 Third International Conference on Digital Data Processing (DDP), 2024
Editore: IEEE
DOI: 10.1109/DDP60485.2023.00019

AwarePrompt: Using Diffusion Models to Create Methods for Measuring Value-Aware AI Architectures

Autori: Kinga Ciupinska, Serena Marchesi, Giulio Abbo, Tony Belpaeme, Agnieszka Wykowska
Pubblicato in: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, 2024
Editore: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0012596400003636

Book chapters (11)

Value-Enriched Population Synthesis: Integrating a Motivational Layer

Autori: Alba Aguilera, Miquel Albertí, Nardine Osman, Georgina Curto
Pubblicato in: Lecture Notes in Computer Science, Value Engineering in Artificial Intelligence, 2025
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-85463-7_1

Vision Language Models as Values Detectors

Autori: Giulio Antonio Abbo, Tony Belpaeme
Pubblicato in: Lecture Notes in Computer Science, Value Engineering in Artificial Intelligence, 2025
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-85463-7_5

Towards the Incorporation of Social Values in Automated Negotiation Strategies

Autori: Laura Rodriguez Cima, Dave De Jonge, Nardine Osman
Pubblicato in: Lecture Notes in Computer Science, Value Engineering in Artificial Intelligence, 2025
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-85463-7_12

On the Relationship Between the Intentional Stance and Robot Responsibility

Autori: Ziggy O’Reilly, Serena Marchesi
Pubblicato in: Intentional Stance Towards Humanoid Robots, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-65483-1_7

Value-Aware Multiagent Systems

Autori: Nardine Osman
Pubblicato in: Lecture Notes in Computer Science, Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XVII, 2025
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-82039-7_3

User Study Design for Identifying the Semantics of Bioethical Principles

Autori: Manel Rodriguez-Soto, Nardine Osman, Carles Sierra, Nieves Montes, Jordi Martinez Roldan, Rocio Cintas Garcia, Cristina Farriols Danes, Montserrat Garcia Retortillo, Silvia Minguez Maso
Pubblicato in: Lecture Notes in Computer Science, Value Engineering in Artificial Intelligence, 2025
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-85463-7_2

Towards Convention-Based Game Strategies

Autori: Shuxian Pan, Carles Sierra
Pubblicato in: Lecture Notes in Computer Science, Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XVI, 2023
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-49133-7_10

Justifications of Moral Responsibility Attributions Towards a Humanoid Robot

Autori: Ziggy O’Reilly, Serena Marchesi, Agnieszka Wykowska
Pubblicato in: Frontiers in Artificial Intelligence and Applications, Social Robots with AI: Prospects, Risks, and Responsible Methods, 2025
Editore: IOS Press
DOI: 10.3233/FAIA241504

Social Value Alignment in Large Language Models

Autori: Giulio Antonio Abbo, Serena Marchesi, Agnieszka Wykowska, Tony Belpaeme
Pubblicato in: Lecture Notes in Computer Science, Value Engineering in Artificial Intelligence, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-58202-8_6

Designing Robots That are Accepted in Human Social Environments: Anthropomorphism, the Intentional Stance, Cultural Norms and Values, and Societal Implications

Autori: Serena Marchesi, Agnieszka Wykowska
Pubblicato in: The De Gruyter Handbook of Robots in Society and Culture, 2024
Editore: De Gruyter
DOI: 10.1515/9783110792270-004

From the Pascal Wager to Value Engineering: A Glance at AI Risks and How to Address Them

Autori: Pablo Noriega, Pompeu Casanovas
Pubblicato in: Lecture Notes in Computer Science, Value Engineering in Artificial Intelligence, 2025
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-85463-7_16

Monographic books (1)

Value Engineering in Artificial Intelligence

Pubblicato in: Lecture Notes in Computer Science, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-58202-8

Diritti di proprietà intellettuale

Other (1)

ValueAlignment: Una librería para el cálculo del alineamiento de valores.

Numero candidatura/pubblicazione: - IDDN1.ES2.0033.5000014.0005.S6.X7.20238.0009.00000010
Data: 2024-12-12
Candidato/i: AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS