Improving social competences of virtual agents through artificial consciousness based on the Attention Schema Theory

Informazioni relative al progetto

ASTOUND

ID dell’accordo di sovvenzione: 101071191

DOI

10.3030/101071191

Progetto chiuso

Data della firma CE 14 Dicembre 2022

Data di avvio 1 Dicembre 2022

Data di completamento 30 Novembre 2025

Finanziato da

• The European Innovation Council (EIC)

Costo totale

€ 3 330 897,50

Contributo UE

€ 3 330 897,50

Coordinato da

UNIVERSIDAD POLITECNICA DE MADRID
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

Demonstrators, pilots, prototypes (3)

Architecture validated
"""Graziano/Turing test"" developed"

“Graziano/Turing test” developed

Cognitive plausibility and role of attention schema established

Documents, reports (6)

Publications describing novel conversational agent
Guidelines for an ethical roadmap for oversight of AI projects
Process of database curation established
Publications describing the conscious conversational agent
Website and project logo

Project logo and website ready

Publications describing the AST architecture

Websites, patent fillings, videos etc. (3)

SME vehicle for IP exploitation incorporated
Patents protecting the architecture and the conscious agent update

Patentability of the architecture and the conscious agent assessed and more patent filed

Study of patentability of the proposed architecture and conscious agent

Preliminary study on the patentability for protecting the architecture and the conscious agent

Data Management Plan (2)

RP2 Update of Data Management Plan

DMP updated

Data Management Plan

DMP generated

Other (3)

Proposal of core morality

Proposal of core morality and its assessment to ensure system safety and allow human oversight

Report on the impact of conscious artificial agents on society
Promoting equality and fairness through self-aware algorithms

Data sets, microdata, etc (2)

Datasets for training the conscious conversational agent
Datasets for training the conscious conversational agent update 2

Pubblicazioni

Conference proceedings (35)

Context or Retrieval? Evaluating RAG Methods for Art and Museum QA System

Autori: Samuel Ramos-Varela, Jaime Bellver-Soler, Marcos Estecha-Garitagoitia, Luis Fernando D’Haro
Pubblicato in: Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology, 2025
Editore: Association for Computational Linguistics

Bias, Subjectivity and Norm in Large Language Models

Autori: Poibeau, T.
Pubblicato in: Aequitas (Fairness and Bias in AI), 2024
Editore: HAL

xDial-Eval: A Multilingual Open-Domain Dialogue Evaluation Benchmark

Autori: Chen Zhang, Luis D’Haro, Chengguang Tang, Ke Shi, Guohua Tang, Haizhou Li
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2023, Numero 5579–5601, 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.FINDINGS-EMNLP.371

Quelques observations sur la notion de biais dans les modèles de langue

Autori: Gallienne P., Poibeau T.
Pubblicato in: Actes de CORIA-TALN 2023. Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), Numero Vol. 3, 2023
Editore: ATALA

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

Autori: Cosimo Della Santina, Carlos Hernandez Corbato, Burak Sisman, Luis A. Leiva, Ioannis Arapakis, Michalis Vakalellis, Jean Vanderdonckt, Luis Fernando D’Haro, Guido Manzi, Cristina Becchio, A ̈ıda Elamrani, Mohsen Alirezaei, Ginevra Castellano, Dimos V. Dim
Pubblicato in: European Robotics Forum, 2024
Editore: European Robotics Forum
DOI: 10.48550/ARXIV.2402.09030

STEPI: System for Triplet Extraction of Personal Information in Dialogue Systems

Autori: Villa Monedero, M., Bellver, J., Ghebriout, M. I. E., De Cordoba, R., & D'Haro, L. F.
Pubblicato in: Iberspeech2024, 2024
Editore: ISCA

Multilingual Speech Emotion Recognition combining Audio and Text using Small Language Models

Autori: Jaime Bellver, Mario Rodríguez Cantelar, Marcos Estecha Garitagoitia, Ricardo De Córdoba Herralde, Luis Fernando D'Haro
Pubblicato in: Iberspeech2024, 2024
Editore: ISCA
DOI: 10.21437/IberSPEECH.2024-43

LLM-Driven Multimodal Fusion for Human Perception Analysis

Autori: Esteban-Romero, S., Martín-Fernández, I., Gil-Martín, M., Griol-Barres, D., Callejas-Carrión, Z., & Fernández-Martínez, F
Pubblicato in: MuSe'24: Proceedings of the 5th on Multimodal Sentiment Analysis Challenge and Workshop: Social Perception and Hum, 2024
Editore: ACM
DOI: 10.1145/3689062.36890

A comprehensive analysis of the effectiveness of large language models as automatic dialogue evaluators

Autori: Zhang, Chen, Luis Fernando D'Haro, Yiming Chen, Malu Zhang, and Haizhou Li.
Pubblicato in: AAAI Conference on Artificial Intelligence, Numero vol. 38, no. 17, pp. 19515-19524., 2024, ISSN 2374-3468
Editore: Advancement of Artifcial Intelligence
DOI: 10.48550/arXiv.2312.15407

Improving Hand Pose Recognition using Localization and Zoom Normalizations over MediaPipe Landmarks

Autori: Remiro Pérez, Miguel Ángel, Gil Martín, Manuel and San Segundo Hernández, Rubén
Pubblicato in: 10th International Electronic Conference on Sensors and Applications session Sensors and Artificial Intelligence, 2023, ISSN 2673-4591
Editore: MDPI
DOI: 10.3390/ECSA-10-16215

DREAM: A Multicultural Multimodal Dataset Linking Dialogues and Realistic Image Sequences

Autori: Juan Mallo, Marcos Estecha-Garitagoitia, Ricardo Cordoba, Luis Fernando D'Haro
Pubblicato in: Proceedings of the Language Resources and Evaluation Conference, Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026), 2026
Editore: European Language Resources Association (ELRA)
DOI: 10.63317/2V7B4XHS2D5G

Synthesizing Olfactory Understanding: Multimodal Language Models for Image–Text Smell Matching

Autori: Esteban-Romero, S., Martín-Fernández, I., Gil-Martín, M., & Fernández-Martínez, F.
Pubblicato in: Symmetry, Numero 17(8), 2025
Editore: MDPI
DOI: 10.3390/SYM17081349

Exploring Video Transformers and Automatic Segment Selection for Memorability Prediction

Autori: Martín-Fernández, I., Romero, S. E., Bellver-Soler, J., Gil-Martín, M., & Martínez, F. F.
Pubblicato in: MediaEval’23: Multimedia Evaluation Workshop,, 2024
Editore: CEUR

THAU-UPM at EmoSPeech-IberLEF2024: Efficient Adaptation of Mono-modal and Multi-modal Large Language Models for Automatic Speech Emotion Recognition

Autori: Esteban-Romero, S., Bellver-Soler, J., Martın-Fernández, I., Gil-Martın, M., D’Haro, L. F., & Fernández-Martınez, F.
Pubblicato in: Iberian Languages Evaluation Forum (IberLEF 2024) at SEPLN2024, 2024, ISSN 1613-0073
Editore: SEPLN

CVQA - Culturally-diverse Multilingual Visual Question Answering Benchmark

Autori: David Romero*👁️, Chenyang Lyu*👁️, Haryo Akbarianto Wibowo👁️, Teresa Lynn, Injy Hamed, Aditya Nanda Kishore, Aishik Mandal, Alina Dragonetti, Artem Abzaliev, Atnafu Lambebo Tonja, Bontu Fufa Balcha, Chenxi Whitehouse, Christian Salamea, Dan John Velasco
Pubblicato in: NeurIPs, 2024
Editore: NeurIPs

Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models

Autori: Chen, Y., Zhang, C., Luo, D., D'Haro, L. F., Tan, R. T., & Li, H.
Pubblicato in: Findings of the Association for Computational Linguistics: ACL 2024, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.FINDINGS-ACL.80

Overview of Dialog System Evaluation Track: Dimensionality, Language, Culture and Safety at DSTC 12.

Autori: John Mendonça, J., Zhang, L., Mallidi, R., Lavie, A., Trancoso, I. D’Haro, L. F., Sedoc, J.
Pubblicato in: Proceedings SigDial 2025, 2025
Editore: SigDial

Beyond single-audio: Advancing multi-audio processing in audio large language models

Autori: Chen, Y., Yue, X., Gao, X., Zhang, C., D'Haro, L. F., Tan, R. T., & Li, H.
Pubblicato in: EMNLP2024, 2024
Editore: Association for Computational Linguistics

Video Memorability Prediction From Jointly-learnt Semantic and Visual Features

Autori: Martín-Fernández, Iván, Ricardo Kleinlein, Cristina Luna-Jiménez, Manuel Gil-Martín, and Fernando Fernández-Martínez
Pubblicato in: 20th International Conference on Content-based Multimedia Indexing, Orleans, France, 2023, ISBN 979-8-4007-0912-8
Editore: ACM

Interpreting Sign Language Recognition using Transformers and MediaPipe Landmarks

Autori: Cristina Luna-Jiménez, Manuel Gil-Martín, Ricardo Kleinlein, Rubén San-Segundo, Fernando Fernández-Martínez
Pubblicato in: 25th ACM International Conference on Multimodal Interaction, 2023, ISBN 979-8-4007-0055-2
Editore: Association for Machinery Computational
DOI: 10.1145/3577190.3614143

Overview of Robust and Multilingual Automatic Evaluation Metricsfor Open-Domain Dialogue Systems at DSTC 11 Track 4

Autori: Mario Rodríguez-Cantelar, Chen Zhang, Chengguang Tang, Ke Shi, Sarik Ghazarian, João Sedoc, Luis Fernando D’Haro, Alexander I. Rudnicky
Pubblicato in: Proceedings of The Eleventh Dialog System Technology Challenge, 2023
Editore: Association for Computational Linguistics

Orchestra: AI-Driven Microservices Architecture to Create Personalized Experiences

Autori: Bellver-Soler, J., Ramos-Varela, S., Guragain, A., Córdoba, R., D’Haro, L. F.
Pubblicato in: IWSDS 2026, 2026
Editore: ACL

Thaurus: An innovative multimodal chatbot based on the next generation of conversational ai. 

Autori: Estecha-Garitagoitia, M., Rodríguez-Cantelar, M., Ruiz, A. G., García, C. G. F., Romero, S. E., Conforto, C., ... & D’Haro, L. F.
Pubblicato in: Proceeding Amazon Alexa Socialbot Grand Challenge 5, 2023
Editore: Amazon

Can Large Sound Event Detection Models Be Accurately Adapted to Specific Acoustic Scenarios?.

Autori: Fernández-Castañón, R., Espinoza-Cuadros, F. M., Perero-Codosero, J. M., Sancho-Lozano, E., & Hernández-Gómez, L. A.
Pubblicato in: International Symposium on Distributed Computing and Artificial Intelligence, 2025
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-80946-0_4

Larger Encoders, Smaller Regressors: Exploring Label Dimensionality Reduction and Multimodal Large Language Models as Feature Extractors for Predicting Social Perception.

Autori: Martín-Fernández, I., Esteban-Romero, S., Bellver-Soler, J., Fernández-Martínez, F., & Gil-Martín, M.
Pubblicato in: Martín-Fernández, I., Esteban-Romero, S., Bellver-Soler, J., Fernández-Martínez, F., & Gil-Martín, M., 2024
Editore: ACM
DOI: 10.1145/3689062.368908

Frequency Analysis and Transfer Learning Across Different Body Sensor Locations in Parkinson’s Disease Detection Using Inertial Signals

Autori: Rey-Díaz, A., Martín-Fernández, I., San-Segundo, R., & Gil-Martín, M.
Pubblicato in: The 11th International Electronic Conference on Sensors and Applications, 2024
Editore: MDPI
DOI: 10.3390/ECSA-11-20507

A Comprehensive Analysis of Parkinson’s Disease Detection Through Inertial Signal Processing

Autori: Gil Martín, Manuel; Esteban Romero, Sergio; Fernández Martínez, Fernando; San Segundo Hernández, Rubén
Pubblicato in: reponame:Archivo Digital UPM, 2024
Editore: ICAART2024
DOI: 10.5220/0012360100003636

Design, Generation and Evaluation of a Synthetic Dialogue Dataset for Contextually Aware Chatbots in Art Museums

Autori: Rachidi, I., Ezzakri, A., Bellver-Soler, J., & D’Haro, L. F.
Pubblicato in: Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology, 2025
Editore: Association for Computational Linguistics

Cutting Through Overload: Efficient Token Dropping for Speech Emotion Recognition in Multimodal Large Language Models

Autori: Bellver-Soler, J., Rodríguez-Cantelar, M., Córdoba, R., & D’Haro, L. F.
Pubblicato in: Proceedings IWSDS 2025, 2025
Editore: Association for Computational Linguistics

Parkinson’s Disease Detection Through Inertial Signals and Posture Insights

Autori: Gil Martín, Manuel; Esteban Romero, Sergio; Fernández Martínez, Fernando; San Segundo Hernández, Rubén
Pubblicato in: Proceedings of the 16th International Conference on Agents and Artificial Intelligence | 16th International Conference on Agents and Artificial Intelligence - ICAART24 | 24/02/2024 | Rome, Italy, 2024
Editore: ICAART
DOI: 10.5220/0012451100003636

A Personalized, Multimodal AI Assistant for Enhancing Museum Visitor Experience

Autori: A. Guragain, J. Bellver-Soler, S. Ramos-Varela, D. Aragón-Diaz, Long, L., L.F. D’Haro
Pubblicato in: Proceedings ALA2025, 2025
Editore: CEUR

Multimodal Audio-Language Model for Speech Emotion Recognition

Autori: Bellver, J., Martín-Fernández, I., Bravo-Pacheco, J. M., Esteban, S., Fernández-Martínez, F., & D'Haro, L. F.
Pubblicato in: odyssey 2024 , 2024
Editore: ISCA
DOI: 10.21437/ODYSSEY.2024-41

ASSIST: A Multi-Agentic Framework for Human-Computer Interaction in Cultural Heritage Settings

Autori: Ramos-Varela, S., Guragain, A., Bellver-Soler, J., Aragón Díaz, D., Lin, L., & D’Haro, L. F.
Pubblicato in: International Conference on Information Management and Big Data, 2025
Editore: SIMBig 2025

Commonsense Generation and Evaluation for Dialogue Systems using Large Language Models

Autori: Estecha-Garitagoitia, M., Zhang, C., Rodríguez-Cantelar, M., & D'Haro, L. F.
Pubblicato in: Proceedings IWSDS 2024, 2024
Editore: ELRA SigSDS

Multimodal and Multilingual Olfactory Matching based on Contrastive Learning

Autori: Esteban-Romero, S., Martín-Fernández, I., Bellver-Soler, J., Gil-Martín, M., & Fernández-Martínez, F.
Pubblicato in: MediaEval’23: Multimedia Evaluation Workshop, 2024
Editore: CEUR

Peer reviewed articles (11)

PoE: A Panel of Experts for Generalized Automatic Dialogue Assessment

Autori: Chen Zhang; Luis Fernando D'Haro; Qiquan Zhang; Thomas Friedrichs; Haizhou Li
Pubblicato in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numero 31, 2023, ISSN 2329-9304
Editore: IEEE
DOI: 10.48550/arXiv.2212.08992

Sign Language Dataset for Automatic Motion Generation

Autori: Villa Monedero, María, Gil Martín, Manuel , Sáez Trigueros, Daniel, Pomirski, Andrzej and San Segundo Hernández, Rubén
Pubblicato in: Journal of Imaging, Numero 9 (12), 2023, ISSN 2313-433X
Editore: MDPI
DOI: 10.3390/JIMAGING9120262

Evaluating emotional and subjective responses in synthetic art-related dialogues: A multi-stage framework with large language models. 

Autori: Luna-Jiménez, C., Gil-Martín, M., D’Haro, L. F., Fernández-Martínez, F., & San-Segundo, R.
Pubblicato in: Expert Systems with Applications, Numero 255, 124524, 2024, ISSN 1873-6793
Editore: ELSEVIER
DOI: 10.1016/J.ESWA.2024.124524

Automatic Detection of Inconsistencies and Hierarchical Topic Classification for Open-Domain Chatbots

Autori: Mario Rodríguez-Cantelar, Marcos Estecha-Garitagoitia, Luis Fernando D’Haro,Fernando Matía, Ricardo Córdoba
Pubblicato in: Applied Sciences, Numero 13 (16), 2023, ISSN 2076-3417
Editore: MDPI
DOI: 10.3390/APP13169055

Overview of the Ninth Dialog System Technology Challenge: DSTC9

Autori: Gunasekara, C., Kim, S., D'haro, L.F., Rastogi, A., Chen, Y.N., Eric, M., Hedayatnia, B., Gopalakrishnan, K., Liu, Y., Huang, C.W. and Hakkani-Tür, D.,
Pubblicato in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numero 32, 4066 - 4076, 2024, ISSN 2329-9304
Editore: IEEE
DOI: 10.1109/TASLP.2024.3426331

Sign Language Motion Generation from Sign Characteristic

Autori: Gil Martín, Manuel , Villa Monedero, María, Pomirski, Andrzej, Sáez Trigueros, Daniel and San Segundo Hernández, Rubén
Pubblicato in: Sensors, Numero 23, 2023, ISSN 1424-8220
Editore: MDPI
DOI: 10.3390/S23239365

Dual Leap Motion Controller 2: A Robust Dataset for Multi-view Hand Pose Recognition

Autori: Manuel Gil-Martín, Marco Raoul Marini, Rubén San-Segundo, Luigi Cinque
Pubblicato in: Scientific Data, Numero 11, 2024, ISSN 2052-4463
Editore: Springer Science and Business Media LLC
DOI: 10.1038/S41597-024-03968-9

A dataset of synthetic art dialogues with ChatGPT

Autori: Gil-Martín, M., Luna-Jiménez, C., Esteban-Romero, S., Estecha-Garitagoitia, M., Fernández-Martínez, F., & D’Haro, L. F.
Pubblicato in: Scientific Data2052-4463, Numero 11(1),825, 2024, ISSN 2052-4463
Editore: Nature Portfolio
DOI: 10.1038/S41597-024-03661-X

Integrating Ethical Principles and Human Rights Based Approach in the EU Artificial Intelligence Act and the Council of Europe Convention on Artificial Intelligence: Interplay of Ethics and Law in the AI Regulation Debate

Autori: Irēna Barkāne, Celia Fernández Aller, Evelyne A. Tauchnitz, Iva Ramuš Cvetkovič, Manja Skočir, Aleš Završnik
Pubblicato in: Journal of the University of Latvia. Law, 2025, ISSN 2592-9364
Editore: University of Latvia
DOI: 10.22364/JULL.19.03

Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialogue

Autori: Jiahui Xu, Feng Jiang, Anningzhe Gao, Luis Fernando D'Haro, Haizhou Li
Pubblicato in: IEEE Transactions on Audio, Speech and Language Processing, Numero 33, 2025, ISSN 2998-4173
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TASLPRO.2025.3623884

Testing Theory of Mind in GPT Models and Humans

Autori: James Strachan, Dalila Albergo, Giulia Borghini, Oriana Pansardi, Eugenio Scaliti, Alessandro Rufo, Guido Manzi, Michael Graziano, Cristina Becchio
Pubblicato in: Research Square, 2023, ISSN 2693-5015
Editore: Research Square
DOI: 10.21203/rs.3.rs-3262385/v1

Book chapters (2)

Aspectos éticos de la inteligencia artificial

Autori: : Tomás Bastarreche Bengoa, Alfonso Egea de Haro, María Mercedes Serrano Pérez, Celia Fernández Aller
Pubblicato in: Derecho y Justicia Global, Numero 3, 2025, ISBN 978-84-7991-660-2
Editore: Universitas

Ethical Risks and Opportunities in Designing Artificial Awareness

Autori: A. Tanevska et al. (including L.D'Haro, C. Fernandez, P. Maurizio, J. Salgado)
Editore: Springer

Other (2)

Attention Schema in Neural Agents

Autori: Liu, Dianbo; Bolotta, Samuele; Zhu, He; Bengio, Yoshua; Dumas, Guillaume
Pubblicato in: ArXiv, 2023
Editore: Cornell University
DOI: 10.48550/arxiv.2305.17375

“Living with IA - A Philosophical Toolkit for Navigating the Conceptual Challenges of Artificial Intelligence Systems”

Autori: Casati R., Maurizio P.
Editore: Institut Jean Nicod