Per Sort
@article{unfairinequality-scidata,
abstract = {This paper introduces a novel benchmark dataset designed to support fairness-oriented research in artificial intelligence within the educational domain. The dataset originates from longitudinal survey data collected by the Agencia Canaria de Calidad Universitaria y Evaluación Educativa, encompassing comprehensive information from students, families, and teachers across the Canary Islands, Spain. It includes detailed student profiles and academic trajectories, covering multiple years of academic performance outcomes. The original data is characterised by a high-dimensional and sparse feature space, which presents challenges for direct application in AI workflows. To address these challenges while minimising the risk of introducing bias during preprocessing, we provide a curated version of the dataset specifically tailored for AI applications. This version preserves the statistical properties of the original data and is accompanied by detailed documentation of the preprocessing steps, including strategies for dimensionality reduction and fairness preservation. The dataset is intended as a resource for the research community, enabling studies on fairness, predictive modeling, and educational analytics. We describe its structure, content, and preparation process.},
apice = {UnfairinequalityScidata},
articleno = 572,
author = {Joseph Giovanelli and Magnini, Matteo and Ciatto, Giovanni and Angel S. Marrero and Andrea Borghesi and Gustavo A. Marrero and Calegari, Roberta},
doi = {10.1038/s41597-026-06827-x},
issn = {2052-4463},
journal = {Scientific Data},
month = mar,
note = {Data Descriptor},
numpages = 12,
openalex = {W7133213904},
publisher = {Nature Portfolio / Springer Nature},
pubmed = {41771897},
title = {Unfair Inequality in Education: A Benchmark for AI-Fairness Research},
url = {https://doi.org/10.1038/s41597-026-06827-x},
urlopenaccess = {https://doi.org/10.1038/s41597-026-06827-x},
volume = 13,
year = 2026
}
abstract = {This paper introduces a novel benchmark dataset designed to support fairness-oriented research in artificial intelligence within the educational domain. The dataset originates from longitudinal survey data collected by the Agencia Canaria de Calidad Universitaria y Evaluación Educativa, encompassing comprehensive information from students, families, and teachers across the Canary Islands, Spain. It includes detailed student profiles and academic trajectories, covering multiple years of academic performance outcomes. The original data is characterised by a high-dimensional and sparse feature space, which presents challenges for direct application in AI workflows. To address these challenges while minimising the risk of introducing bias during preprocessing, we provide a curated version of the dataset specifically tailored for AI applications. This version preserves the statistical properties of the original data and is accompanied by detailed documentation of the preprocessing steps, including strategies for dimensionality reduction and fairness preservation. The dataset is intended as a resource for the research community, enabling studies on fairness, predictive modeling, and educational analytics. We describe its structure, content, and preparation process.},
apice = {UnfairinequalityScidata},
articleno = 572,
author = {Joseph Giovanelli and Magnini, Matteo and Ciatto, Giovanni and Angel S. Marrero and Andrea Borghesi and Gustavo A. Marrero and Calegari, Roberta},
doi = {10.1038/s41597-026-06827-x},
issn = {2052-4463},
journal = {Scientific Data},
month = mar,
note = {Data Descriptor},
numpages = 12,
openalex = {W7133213904},
publisher = {Nature Portfolio / Springer Nature},
pubmed = {41771897},
title = {Unfair Inequality in Education: A Benchmark for AI-Fairness Research},
url = {https://doi.org/10.1038/s41597-026-06827-x},
urlopenaccess = {https://doi.org/10.1038/s41597-026-06827-x},
volume = 13,
year = 2026
}
@article{llmoracles-kbs310,
acm = {10.1016/j.knosys.2024.112940},
apice = {LlmoraclesKbs310},
articleno = 112940,
arxiv = {2404.04108},
author = {Ciatto, Giovanni and Agiollo, Andrea and Magnini, Matteo and Omicini, Andrea},
dblp = {journals/kbs/CiattoAMO25},
doi = {10.1016/j.knosys.2024.112940},
iris = {11585/1001205},
issn = {0950-7051},
journal = {Knowledge-Based Systems},
keywords = {Ontology population; Large language models; Nutrition; Automation; Domain-specific knowledge},
lens = {002-808-574-876-090},
month = {15~} # feb,
numpages = 22,
openalex = {W4406141444},
opencitations = {0606112740},
pages = {1--22},
publisher = {Elsevier B.V.},
scholar = {12608317221311042342},
scopus = {2-s2.0-85214522484},
title = {Large language models as oracles for instantiating ontologies with domain-specific knowledge},
url = {https://www.sciencedirect.com/science/article/pii/S0950705124015740},
urlopenaccess = {https://www.sciencedirect.com/science/article/pii/S0950705124015740},
volume = 310,
wos = {WOS:001397431800001},
year = 2025
}
acm = {10.1016/j.knosys.2024.112940},
apice = {LlmoraclesKbs310},
articleno = 112940,
arxiv = {2404.04108},
author = {Ciatto, Giovanni and Agiollo, Andrea and Magnini, Matteo and Omicini, Andrea},
dblp = {journals/kbs/CiattoAMO25},
doi = {10.1016/j.knosys.2024.112940},
iris = {11585/1001205},
issn = {0950-7051},
journal = {Knowledge-Based Systems},
keywords = {Ontology population; Large language models; Nutrition; Automation; Domain-specific knowledge},
lens = {002-808-574-876-090},
month = {15~} # feb,
numpages = 22,
openalex = {W4406141444},
opencitations = {0606112740},
pages = {1--22},
publisher = {Elsevier B.V.},
scholar = {12608317221311042342},
scopus = {2-s2.0-85214522484},
title = {Large language models as oracles for instantiating ontologies with domain-specific knowledge},
url = {https://www.sciencedirect.com/science/article/pii/S0950705124015740},
urlopenaccess = {https://www.sciencedirect.com/science/article/pii/S0950705124015740},
volume = 310,
wos = {WOS:001397431800001},
year = 2025
}
@article{privacypreserving-smhealth36,
abstract = {Medical chatbots are becoming a basic component in telemedicine, propelled by advancements in Large Language Models (LLMs). However, LLMs' integration into clinical settings comes with several issues, with privacy concerns being particularly significant. The paper proposes a tailored architectural solution and an information workflow that address privacy issues, while preserving the benefits of LLMs. We examine two solutions to prevent the disclosure of sensitive information: (i) a filtering mechanism that processes sensitive data locally but leverage a robust OpenAI's online LLM for engaging with the user effectively, and (ii) a fully local deployment of open-source LLMs. The effectiveness of these solutions is assessed in the context of hypertension management across various tasks, ranging from intent recognition to reliable and emphatic conversation. Interestingly, while the first solution proved to be more robust in intent recognition, an evaluation by domain experts of the models' responses, based on reliability and empathetic principles, revealed that two out of six open LLMs received the highest scores. The study underscores the viability of incorporating LLMs into medical chatbots. In particular, our findings suggest that open LLMs can offer a privacy-preserving, yet promising, alternative to external LLM services, ensuring safer and more reliable telemedicine practices. Future efforts will focus on fine-tuning local models to enhance their performance across all tasks.},
apice = {PrivacypreservingSmhealth36},
articleno = 100552,
author = {Montagna, Sara and Stefano Ferretti and Lorenz Cuno Klopfenstein and Michelangelo Ungolo and Martino Francesco Pengo and Aguzzi, Gianluca and Magnini, Matteo},
doi = {10.1016/j.smhl.2025.100552},
eissn = {2352-6491},
issn = {2352-6483},
journal = {Smart Health},
keywords = {Large Language Model, Medical chatbot, Patient self-management, Patient empowerment},
month = mar,
numpages = 13,
openalex = {W4408237661},
publisher = {Elsevier Inc.},
title = {Privacy-preserving LLM-based chatbots for hypertensive patient self-management},
url = {https://www.sciencedirect.com/science/article/pii/S2352648325000133},
urlopenaccess = {https://www.sciencedirect.com/science/article/pii/S2352648325000133},
volume = 36,
year = 2025
}
abstract = {Medical chatbots are becoming a basic component in telemedicine, propelled by advancements in Large Language Models (LLMs). However, LLMs' integration into clinical settings comes with several issues, with privacy concerns being particularly significant. The paper proposes a tailored architectural solution and an information workflow that address privacy issues, while preserving the benefits of LLMs. We examine two solutions to prevent the disclosure of sensitive information: (i) a filtering mechanism that processes sensitive data locally but leverage a robust OpenAI's online LLM for engaging with the user effectively, and (ii) a fully local deployment of open-source LLMs. The effectiveness of these solutions is assessed in the context of hypertension management across various tasks, ranging from intent recognition to reliable and emphatic conversation. Interestingly, while the first solution proved to be more robust in intent recognition, an evaluation by domain experts of the models' responses, based on reliability and empathetic principles, revealed that two out of six open LLMs received the highest scores. The study underscores the viability of incorporating LLMs into medical chatbots. In particular, our findings suggest that open LLMs can offer a privacy-preserving, yet promising, alternative to external LLM services, ensuring safer and more reliable telemedicine practices. Future efforts will focus on fine-tuning local models to enhance their performance across all tasks.},
apice = {PrivacypreservingSmhealth36},
articleno = 100552,
author = {Montagna, Sara and Stefano Ferretti and Lorenz Cuno Klopfenstein and Michelangelo Ungolo and Martino Francesco Pengo and Aguzzi, Gianluca and Magnini, Matteo},
doi = {10.1016/j.smhl.2025.100552},
eissn = {2352-6491},
issn = {2352-6483},
journal = {Smart Health},
keywords = {Large Language Model, Medical chatbot, Patient self-management, Patient empowerment},
month = mar,
numpages = 13,
openalex = {W4408237661},
publisher = {Elsevier Inc.},
title = {Privacy-preserving LLM-based chatbots for hypertensive patient self-management},
url = {https://www.sciencedirect.com/science/article/pii/S2352648325000133},
urlopenaccess = {https://www.sciencedirect.com/science/article/pii/S2352648325000133},
volume = 36,
year = 2025
}
@article{skeislr-csur56,
acm = {3645103},
apice = {SkeislrCsur56},
articleno = 161,
author = {Ciatto, Giovanni and Sabbatini, Federico and Agiollo, Andrea and Magnini, Matteo and Omicini, Andrea},
dblp = {journals/csur/CiattoSAMO24},
doi = {10.1145/3645103},
eissn = {1557-734},
iris = {11585/969235},
issn = {0360-0300},
journal = {ACM Computing Surveys},
keywords = {Logic; Machine learning theory; Hybrid symbolic-numeric methods; Knowledge representation and reasoning},
lens = {143-064-043-213-611},
month = jun,
number = 6,
numpages = 35,
openalex = {W4391645809},
opencitations = {06804657002},
pages = {1--35},
publisher = {ACM},
scholar = {13701373869146776438},
scopus = {2-s2.0-85188835517},
semanticscholar = {267611660},
title = {Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review},
url = {https://dl.acm.org/doi/10.1145/3645103},
urlopenaccess = {https://dl.acm.org/doi/pdf/10.1145/3645103},
urlpdf = {https://dl.acm.org/doi/pdf/10.1145/3645103},
volume = 56,
wos = {WOS:001208566200027},
year = 2024
}
acm = {3645103},
apice = {SkeislrCsur56},
articleno = 161,
author = {Ciatto, Giovanni and Sabbatini, Federico and Agiollo, Andrea and Magnini, Matteo and Omicini, Andrea},
dblp = {journals/csur/CiattoSAMO24},
doi = {10.1145/3645103},
eissn = {1557-734},
iris = {11585/969235},
issn = {0360-0300},
journal = {ACM Computing Surveys},
keywords = {Logic; Machine learning theory; Hybrid symbolic-numeric methods; Knowledge representation and reasoning},
lens = {143-064-043-213-611},
month = jun,
number = 6,
numpages = 35,
openalex = {W4391645809},
opencitations = {06804657002},
pages = {1--35},
publisher = {ACM},
scholar = {13701373869146776438},
scopus = {2-s2.0-85188835517},
semanticscholar = {267611660},
title = {Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review},
url = {https://dl.acm.org/doi/10.1145/3645103},
urlopenaccess = {https://dl.acm.org/doi/pdf/10.1145/3645103},
urlpdf = {https://dl.acm.org/doi/pdf/10.1145/3645103},
volume = 56,
wos = {WOS:001208566200027},
year = 2024
}
@article{kins-jlc33,
apice = {KinsJlc33},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
dblp = {journals/logcom/MagniniCO23},
doi = {10.1093/logcom/exad037},
eissn = {1465-363X},
iris = {11585/950567},
issn = {0955-792X},
journal = {Journal of Logic and Computation},
keywords = {neural network, expalinable AI, symbolic knowledge injection, KINS, PSyKI},
lens = {159-289-375-475-253},
month = dec,
number = 8,
numpages = 19,
openalex = {W4382319513},
pages = {1832--1850},
publisher = {Oxford University Press},
scholar = {2353304508513748358},
scopus = {2-s2.0-85179896166},
semanticscholar = {266726315},
title = {Knowledge injection of {D}atalog rules via Neural Network Structuring with {KINS}},
url = {https://academic.oup.com/logcom/article/33/8/1832/7190990},
volume = 33,
wos = {WOS:001003002200001},
year = 2023
}
apice = {KinsJlc33},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
dblp = {journals/logcom/MagniniCO23},
doi = {10.1093/logcom/exad037},
eissn = {1465-363X},
iris = {11585/950567},
issn = {0955-792X},
journal = {Journal of Logic and Computation},
keywords = {neural network, expalinable AI, symbolic knowledge injection, KINS, PSyKI},
lens = {159-289-375-475-253},
month = dec,
number = 8,
numpages = 19,
openalex = {W4382319513},
pages = {1832--1850},
publisher = {Oxford University Press},
scholar = {2353304508513748358},
scopus = {2-s2.0-85179896166},
semanticscholar = {266726315},
title = {Knowledge injection of {D}atalog rules via Neural Network Structuring with {KINS}},
url = {https://academic.oup.com/logcom/article/33/8/1832/7190990},
volume = 33,
wos = {WOS:001003002200001},
year = 2023
}
@article{skiqos-jaamas37,
apice = {SkiqosJaamas37},
articleno = 27,
author = {Agiollo, Andrea and Rafanelli, Andrea and Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
dblp = {journals/aamas/AgiolloRMCO23},
doi = {10.1007/s10458-023-09609-6},
iris = {11585/932553},
issn = {1573-7454},
journal = {Autonomous Agents and Multi-Agent Systems},
keywords = {symbolic knowledge injection, quality of service, efficiency, robustness, PSyKI},
lens = {030-976-235-615-062},
month = jun,
number = 2,
numpages = 30,
openalex = {W4381996778},
pages = {1--30},
scholar = {6493335879803556297},
scopus = {2-s2.0-85162972232},
semanticscholar = {259234850},
title = {Symbolic Knowledge Injection meets Intelligent Agents: {QoS} metrics and experiments},
url = {https://link.springer.com/10.1007/s10458-023-09609-6},
volume = 37,
wos = {WOS:001013184000001},
year = 2023
}
apice = {SkiqosJaamas37},
articleno = 27,
author = {Agiollo, Andrea and Rafanelli, Andrea and Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
dblp = {journals/aamas/AgiolloRMCO23},
doi = {10.1007/s10458-023-09609-6},
iris = {11585/932553},
issn = {1573-7454},
journal = {Autonomous Agents and Multi-Agent Systems},
keywords = {symbolic knowledge injection, quality of service, efficiency, robustness, PSyKI},
lens = {030-976-235-615-062},
month = jun,
number = 2,
numpages = 30,
openalex = {W4381996778},
pages = {1--30},
scholar = {6493335879803556297},
scopus = {2-s2.0-85162972232},
semanticscholar = {259234850},
title = {Symbolic Knowledge Injection meets Intelligent Agents: {QoS} metrics and experiments},
url = {https://link.springer.com/10.1007/s10458-023-09609-6},
volume = 37,
wos = {WOS:001013184000001},
year = 2023
}
@article{skerecommender-cmbp235,
acm = {10.1016/j.cmpb.2023.107536},
apice = {SkerecommenderCmbp235},
articleno = 107536,
author = {Magnini, Matteo and Ciatto, Giovanni and Cantürk, Furkan and Aydoǧan, Reyhan and Omicini, Andrea},
dblp = {journals/cmpb/MagniniCCAO23},
doi = {10.1016/j.cmpb.2023.107536},
iris = {11585/923772},
issn = {0169-2607},
journal = {Computer Methods and Programs in Biomedicine},
keywords = {explainable artificial intelligence, symbolic knowledge extraction, recommendation systems, nutrition, neural networks},
lens = {046-208-009-872-49X},
month = jun,
numpages = 32,
openalex = {W4362641065},
pubmed = {37060685},
scholar = {14455392383017605572},
scopus = {2-s2.0-85152230884},
semanticscholar = {261426939},
title = {Symbolic Knowledge Extraction for Explainable Nutritional Recommenders},
url = {https://www.sciencedirect.com/science/article/pii/S0169260723002018},
volume = 235,
wos = {WOS:000983750400001},
year = 2023
}
acm = {10.1016/j.cmpb.2023.107536},
apice = {SkerecommenderCmbp235},
articleno = 107536,
author = {Magnini, Matteo and Ciatto, Giovanni and Cantürk, Furkan and Aydoǧan, Reyhan and Omicini, Andrea},
dblp = {journals/cmpb/MagniniCCAO23},
doi = {10.1016/j.cmpb.2023.107536},
iris = {11585/923772},
issn = {0169-2607},
journal = {Computer Methods and Programs in Biomedicine},
keywords = {explainable artificial intelligence, symbolic knowledge extraction, recommendation systems, nutrition, neural networks},
lens = {046-208-009-872-49X},
month = jun,
numpages = 32,
openalex = {W4362641065},
pubmed = {37060685},
scholar = {14455392383017605572},
scopus = {2-s2.0-85152230884},
semanticscholar = {261426939},
title = {Symbolic Knowledge Extraction for Explainable Nutritional Recommenders},
url = {https://www.sciencedirect.com/science/article/pii/S0169260723002018},
volume = 235,
wos = {WOS:000983750400001},
year = 2023
}
@inproceedings{nl2unifol-skilledllm2026,
abstract = {Automatic translation of Natural Language (NL) sentences into logic representation – such as First-Order Logic (FOL) formulae – is a task of great interest for many communities, including Knowledge Representation (KR), Natural Language Processing (NLP), normative Artificial Intelligence (AI), and AI in general. Recently, an increasing number of works have explored the use of Large Language Models (LLMs) to translate NL into FOL, with promising results. However, existing works mostly focus on the translation of a single NL sentence at a time, resulting in independent formulae that do not share a common predicate and constant name space. This work presents a new framework – namely Natural Language to Uniform First Order Logic (NL2UNIFOL) – that leverages LLMs to translate NL sentences into a uniform FOL theory, where formulae share the same vocabulary. NL2UNIFOL is an end-to-end pipeline that: (i) translates NL sentences into preliminary FOL formulae; (ii) identifies and safely merges predicate and constant names to obtain a uniform vocabulary; (iii) finally generates the final FOL theory. We use NL-FOL pairs from the MALLS dataset to validate our framework. Results show that in the majority of cases NL2UNIFOL is able to correctly create clusters of predicate and constant names to be merged together, which allows to obtain a uniform FOL theory. We also recognise that there are still a numerous amount of cases in which the represented name and the representative name semantically diverge, which motivates future work to further improve the symbol clustering process.},
apice = {Nl2unifolSkilledllm2026},
author = {Magnini, Matteo and Davide Liga and Luca Pasetto},
booktitle = {Proceedings of the Joint Workshop on Statistics and Knowledge Integration for Logic, Learning, Ethical Decisions, and LLMs (SKILLED-LLMs 2026) co-located with the Federated Logic Conference 2026 (FLoC 2026), Lisbon, Portugal, July 18, 2026},
dblp = {conf/skilled-llms/MagniniLP26},
editor = {Ha Thanh Nguyen and Francesca Toni and Kostas Stathis and Ken Satoh and Randy Goebel and Francesco Chiariello and Yves Lespérance and Magnini, Matteo and Sabbatini, Federico and Elena Umili and Nourhan Ehab and Mervat Abu-Elkheir},
issn = {1613-0073},
keywords = {Natural Language Processing, First-Order Logic, Large Language Models, Knowledge Representation},
numpages = 18,
pages = {126--143},
publisher = {Sun SITE Central Europe, RWTH Aachen University},
series = {CEUR Workshop Proceedings},
title = {NL2UNIFOL: From Natural Language Sentences to Uniform First-Order Logic Formulae},
url = {https://ceur-ws.org/Vol-4229/paper13.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-4229/paper13.pdf},
urlpdf = {https://ceur-ws.org/Vol-4229/paper13.pdf},
volume = 4229,
year = 2026
}
abstract = {Automatic translation of Natural Language (NL) sentences into logic representation – such as First-Order Logic (FOL) formulae – is a task of great interest for many communities, including Knowledge Representation (KR), Natural Language Processing (NLP), normative Artificial Intelligence (AI), and AI in general. Recently, an increasing number of works have explored the use of Large Language Models (LLMs) to translate NL into FOL, with promising results. However, existing works mostly focus on the translation of a single NL sentence at a time, resulting in independent formulae that do not share a common predicate and constant name space. This work presents a new framework – namely Natural Language to Uniform First Order Logic (NL2UNIFOL) – that leverages LLMs to translate NL sentences into a uniform FOL theory, where formulae share the same vocabulary. NL2UNIFOL is an end-to-end pipeline that: (i) translates NL sentences into preliminary FOL formulae; (ii) identifies and safely merges predicate and constant names to obtain a uniform vocabulary; (iii) finally generates the final FOL theory. We use NL-FOL pairs from the MALLS dataset to validate our framework. Results show that in the majority of cases NL2UNIFOL is able to correctly create clusters of predicate and constant names to be merged together, which allows to obtain a uniform FOL theory. We also recognise that there are still a numerous amount of cases in which the represented name and the representative name semantically diverge, which motivates future work to further improve the symbol clustering process.},
apice = {Nl2unifolSkilledllm2026},
author = {Magnini, Matteo and Davide Liga and Luca Pasetto},
booktitle = {Proceedings of the Joint Workshop on Statistics and Knowledge Integration for Logic, Learning, Ethical Decisions, and LLMs (SKILLED-LLMs 2026) co-located with the Federated Logic Conference 2026 (FLoC 2026), Lisbon, Portugal, July 18, 2026},
dblp = {conf/skilled-llms/MagniniLP26},
editor = {Ha Thanh Nguyen and Francesca Toni and Kostas Stathis and Ken Satoh and Randy Goebel and Francesco Chiariello and Yves Lespérance and Magnini, Matteo and Sabbatini, Federico and Elena Umili and Nourhan Ehab and Mervat Abu-Elkheir},
issn = {1613-0073},
keywords = {Natural Language Processing, First-Order Logic, Large Language Models, Knowledge Representation},
numpages = 18,
pages = {126--143},
publisher = {Sun SITE Central Europe, RWTH Aachen University},
series = {CEUR Workshop Proceedings},
title = {NL2UNIFOL: From Natural Language Sentences to Uniform First-Order Logic Formulae},
url = {https://ceur-ws.org/Vol-4229/paper13.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-4229/paper13.pdf},
urlpdf = {https://ceur-ws.org/Vol-4229/paper13.pdf},
volume = 4229,
year = 2026
}
@inproceedings{slmmobiledevices-percomworkshops2026,
abstract = {Large language models (LLMs) are increasingly being adopted across diverse healthcare scenarios. However, their deployment on mobile devices is hindered by significant resource demands and privacy concerns associated with cloud-based solutions. Ensuring reliable, private, and accessible healthcare support on mobile devices requires models that are both performant and lightweight. Therefore, small language models (SLMs) present a promising solution for enabling on-device healthcare support. This study explores the trade-offs between model size and performance necessary to effectively execute general medical question-answering tasks on mobile devices. To evaluate this, we present MedicoAI, a cross-platform application designed to support local SLMs inference across mobile, web, and desktop environments. We evaluated four state-of-the-art SLMs with model sizes under 1GB using two prompt templates (a standard baseline and one with medical safety constraints) and three word-limit configurations. Our findings highlight the viability of deploying SLMs for medical question-answering on mobile devices while maintaining user privacy and resource efficiency.},
apice = {SlmmobiledevicesPercomworkshops2026},
author = {Aqila Farahmand and Montagna, Sara and Alessandro Bogliolo and Stefano Ferretti and Magnini, Matteo},
booktitle = {2026 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)},
dblp = {conf/percom/FarahmandMBFM26},
doi = {10.1109/PerComWorkshops68308.2026.11585382},
isbn = {979-8-3315-7615-8},
keywords = {Small Language Models, Mobile Health, Patient Self-Management, Local Models, Privacy-preserving},
month = {16-20 March},
note = {5th International Workshop on Telemedicine and e-Health in the digital society (TELMED 2026)},
numpages = 6,
openalex = {W7167064743},
pages = {1--6},
publisher = {IEEE},
title = {Performant and Small: Can We Have Both? SLMs on Mobile Devices for Healthcare Chatbots},
url = {https://ieeexplore.ieee.org/document/11585382},
urlpdf = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11585382},
year = 2026
}
abstract = {Large language models (LLMs) are increasingly being adopted across diverse healthcare scenarios. However, their deployment on mobile devices is hindered by significant resource demands and privacy concerns associated with cloud-based solutions. Ensuring reliable, private, and accessible healthcare support on mobile devices requires models that are both performant and lightweight. Therefore, small language models (SLMs) present a promising solution for enabling on-device healthcare support. This study explores the trade-offs between model size and performance necessary to effectively execute general medical question-answering tasks on mobile devices. To evaluate this, we present MedicoAI, a cross-platform application designed to support local SLMs inference across mobile, web, and desktop environments. We evaluated four state-of-the-art SLMs with model sizes under 1GB using two prompt templates (a standard baseline and one with medical safety constraints) and three word-limit configurations. Our findings highlight the viability of deploying SLMs for medical question-answering on mobile devices while maintaining user privacy and resource efficiency.},
apice = {SlmmobiledevicesPercomworkshops2026},
author = {Aqila Farahmand and Montagna, Sara and Alessandro Bogliolo and Stefano Ferretti and Magnini, Matteo},
booktitle = {2026 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)},
dblp = {conf/percom/FarahmandMBFM26},
doi = {10.1109/PerComWorkshops68308.2026.11585382},
isbn = {979-8-3315-7615-8},
keywords = {Small Language Models, Mobile Health, Patient Self-Management, Local Models, Privacy-preserving},
month = {16-20 March},
note = {5th International Workshop on Telemedicine and e-Health in the digital society (TELMED 2026)},
numpages = 6,
openalex = {W7167064743},
pages = {1--6},
publisher = {IEEE},
title = {Performant and Small: Can We Have Both? SLMs on Mobile Devices for Healthcare Chatbots},
url = {https://ieeexplore.ieee.org/document/11585382},
urlpdf = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11585382},
year = 2026
}
@inproceedings{activelylearning-ecai2025,
abstract = {In active learning, a learner attempts to learn from a teacher by posing questions. The questions made by the learner are called membership queries and are answered with `yes' or `no'. This kind of query is often studied as part of a communication protocol that also includes equivalence queries. Intuitively, equivalence queries ask whether the idea of the learner about the knowledge of the teacher is correct or not. If not, then the teacher should provide a counterexample showing the difference. Here, we consider the teacher as a large language model (LLM) and study the case in which knowledge is expressed as an EL terminology. Membership queries ask whether concept inclusions are true or not. E.g., ``Can algae be considered a subcategory of plant?''. Equivalence queries are simulated by a sample with concept inclusions labelled as positive or negative. We present a non-trivial extension of the ExactLearner tool to extract EL terminologies from LLMs. Given the relevant symbols as input (e.g., algae, plant, etc.), the tool tries to find how these symbols should be logically connected by posing questions to LLMs. To evaluate the approach, we present performance results of the ExactLearner in the task of reconstructing existing EL terminologies.},
apice = {ActivelylearningEcai2025},
author = {Magnini, Matteo and Squarcialupi, Riccardo and Martin T. Sterri and Ana Ozaki},
booktitle = {28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy – Including 14th Conference on Prestigious Applications of Intelligent Systems (PAIS 2025)},
doi = {10.3233/FAIA251009},
editor = {Inês Lynce and Nello Murano and Mauro Vallati and Serena Villata and Chesani, Federico and Milano, Michela and Omicini, Andrea and Mehdi Dastani},
isbn = {978-1-64368-631-8},
numpages = 8,
openalex = {W4415428417},
pages = {1792--1799},
publisher = {IOS Press},
series = {Frontiers in Artificial Intelligence and Applications},
title = {Actively Learning EL Terminologies from Large Language Models},
url = {https://ebooks.iospress.nl/doi/10.3233/FAIA251009},
urlopenaccess = {https://ebooks.iospress.nl/doi/10.3233/FAIA251009},
volume = 413,
year = 2025
}
abstract = {In active learning, a learner attempts to learn from a teacher by posing questions. The questions made by the learner are called membership queries and are answered with `yes' or `no'. This kind of query is often studied as part of a communication protocol that also includes equivalence queries. Intuitively, equivalence queries ask whether the idea of the learner about the knowledge of the teacher is correct or not. If not, then the teacher should provide a counterexample showing the difference. Here, we consider the teacher as a large language model (LLM) and study the case in which knowledge is expressed as an EL terminology. Membership queries ask whether concept inclusions are true or not. E.g., ``Can algae be considered a subcategory of plant?''. Equivalence queries are simulated by a sample with concept inclusions labelled as positive or negative. We present a non-trivial extension of the ExactLearner tool to extract EL terminologies from LLMs. Given the relevant symbols as input (e.g., algae, plant, etc.), the tool tries to find how these symbols should be logically connected by posing questions to LLMs. To evaluate the approach, we present performance results of the ExactLearner in the task of reconstructing existing EL terminologies.},
apice = {ActivelylearningEcai2025},
author = {Magnini, Matteo and Squarcialupi, Riccardo and Martin T. Sterri and Ana Ozaki},
booktitle = {28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy – Including 14th Conference on Prestigious Applications of Intelligent Systems (PAIS 2025)},
doi = {10.3233/FAIA251009},
editor = {Inês Lynce and Nello Murano and Mauro Vallati and Serena Villata and Chesani, Federico and Milano, Michela and Omicini, Andrea and Mehdi Dastani},
isbn = {978-1-64368-631-8},
numpages = 8,
openalex = {W4415428417},
pages = {1792--1799},
publisher = {IOS Press},
series = {Frontiers in Artificial Intelligence and Applications},
title = {Actively Learning EL Terminologies from Large Language Models},
url = {https://ebooks.iospress.nl/doi/10.3233/FAIA251009},
urlopenaccess = {https://ebooks.iospress.nl/doi/10.3233/FAIA251009},
volume = 413,
year = 2025
}
@inproceedings{dslnesy-ansya2025,
apice = {DslNesyAnsya2025},
author = {Matteini, Mattia and Ciatto, Giovanni and Magnini, Matteo and Kuru, Emre and Aydo{\u g}an, Reyhan and Omicini, Andrea},
booktitle = {ANSyA 2025: Advanced Neuro-Symbolic Applications},
dblp = {conf/ansya/MatteiniCMKAO25},
editor = {Agiollo, Andrea and Bardhi, Enkeleda and Ciatto, Giovanni and Dumancic, Giovanni and Marra, Giuseppe},
iris = {11585/1048553},
keywords = {symbolic knowledge injection, SKI-lang, NeSy, language, Python},
month = oct,
note = {Proceedings of the 1st International Workshop on Advanced Neuro-Symbolic Applications co-located with the 28th European Conference on Artificial Intelligence (ECAI 2025)},
numpages = 9,
pages = {84--92},
publisher = {CEUR-WS},
scholar = {5084539886289942855},
scopus = {2-s2.0-105038978909},
series = {CEUR Workshop Proceedings},
title = {A Domain-Specific Language for {NeSy} Focussing on Symbolic Knowledge Injection},
url = {https://ceur-ws.org/Vol-4125/paper_21.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-4125/paper_21.pdf},
urlpdf = {https://ceur-ws.org/Vol-4125/paper_21.pdf},
volume = 4125,
wos = {WOS:001664416600013},
year = 2025
}
apice = {DslNesyAnsya2025},
author = {Matteini, Mattia and Ciatto, Giovanni and Magnini, Matteo and Kuru, Emre and Aydo{\u g}an, Reyhan and Omicini, Andrea},
booktitle = {ANSyA 2025: Advanced Neuro-Symbolic Applications},
dblp = {conf/ansya/MatteiniCMKAO25},
editor = {Agiollo, Andrea and Bardhi, Enkeleda and Ciatto, Giovanni and Dumancic, Giovanni and Marra, Giuseppe},
iris = {11585/1048553},
keywords = {symbolic knowledge injection, SKI-lang, NeSy, language, Python},
month = oct,
note = {Proceedings of the 1st International Workshop on Advanced Neuro-Symbolic Applications co-located with the 28th European Conference on Artificial Intelligence (ECAI 2025)},
numpages = 9,
pages = {84--92},
publisher = {CEUR-WS},
scholar = {5084539886289942855},
scopus = {2-s2.0-105038978909},
series = {CEUR Workshop Proceedings},
title = {A Domain-Specific Language for {NeSy} Focussing on Symbolic Knowledge Injection},
url = {https://ceur-ws.org/Vol-4125/paper_21.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-4125/paper_21.pdf},
urlpdf = {https://ceur-ws.org/Vol-4125/paper_21.pdf},
volume = 4125,
wos = {WOS:001664416600013},
year = 2025
}
@inproceedings{nesyaichronicdiseasetelmed2025,
apice = {NeSyAIChronicDiseaseTelmed2025},
author = {Magnini, Matteo and Ciatto, Giovanni and Ahmet Emre Kuru and Christel Sirocchi and Montagna, Sara},
booktitle = {2025 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)},
doi = {10.1109/PerComWorkshops65533.2025.00106},
editor = {Piero Castoldi and Anna Lina Ruscelli and Lorenzo Mucchi and Matti Hämäläinen},
isbn = {979-8-3315-3553-7},
keywords = {Symbolic Knowledge Injection, Neurosymbolic AI, Clinical protocols and data},
month = {17-21 March},
note = {4th International Workshop on Telemedicine and e-Health evolution in the new era of social distancing (TELMED 2025)},
pages = {446--451},
publisher = {IEEE},
title = {Neuro-Symbolic AI for Supporting Chronic Disease Diagnosis and Monitoring},
url = {https://ieeexplore.ieee.org/document/11038535},
urlpdf = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11038535},
year = 2025
}
apice = {NeSyAIChronicDiseaseTelmed2025},
author = {Magnini, Matteo and Ciatto, Giovanni and Ahmet Emre Kuru and Christel Sirocchi and Montagna, Sara},
booktitle = {2025 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)},
doi = {10.1109/PerComWorkshops65533.2025.00106},
editor = {Piero Castoldi and Anna Lina Ruscelli and Lorenzo Mucchi and Matti Hämäläinen},
isbn = {979-8-3315-3553-7},
keywords = {Symbolic Knowledge Injection, Neurosymbolic AI, Clinical protocols and data},
month = {17-21 March},
note = {4th International Workshop on Telemedicine and e-Health evolution in the new era of social distancing (TELMED 2025)},
pages = {446--451},
publisher = {IEEE},
title = {Neuro-Symbolic AI for Supporting Chronic Disease Diagnosis and Monitoring},
url = {https://ieeexplore.ieee.org/document/11038535},
urlpdf = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11038535},
year = 2025
}
@inproceedings{exact-learning-llm-dl2024,
apice = {OntologyDL2024},
articleno = 32,
author = {Magnini, Matteo and Ana Ozaki and Squarcialupi, Riccardo},
booktitle = {Proceedings of the 37th International Workshop on Description Logics {(DL} 2024), Bergen, Norway, June 18-21, 2024},
dblp = {conf/dlog/MagniniOS24},
editor = {Laura Giordano and Jean Christoph Jung and Ana Ozaki},
iris = {11585/996984},
issn = {1613-0073},
keywords = {Active Learning, Ontologies, Language Models},
month = jun,
note = {Extended abstract},
numpages = 5,
pages = {1--5},
publisher = {CEUR-WS.org},
series = {{CEUR} Workshop Proceedings},
title = {Actively Learning Ontologies from LLMs: First Results (Extended Abstract)},
url = {https://ceur-ws.org/Vol-3739/abstract-18.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-3739/abstract-18.pdf},
urlpdf = {https://ceur-ws.org/Vol-3739/abstract-18.pdf},
volume = 3739,
year = 2024
}
apice = {OntologyDL2024},
articleno = 32,
author = {Magnini, Matteo and Ana Ozaki and Squarcialupi, Riccardo},
booktitle = {Proceedings of the 37th International Workshop on Description Logics {(DL} 2024), Bergen, Norway, June 18-21, 2024},
dblp = {conf/dlog/MagniniOS24},
editor = {Laura Giordano and Jean Christoph Jung and Ana Ozaki},
iris = {11585/996984},
issn = {1613-0073},
keywords = {Active Learning, Ontologies, Language Models},
month = jun,
note = {Extended abstract},
numpages = 5,
pages = {1--5},
publisher = {CEUR-WS.org},
series = {{CEUR} Workshop Proceedings},
title = {Actively Learning Ontologies from LLMs: First Results (Extended Abstract)},
url = {https://ceur-ws.org/Vol-3739/abstract-18.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-3739/abstract-18.pdf},
urlpdf = {https://ceur-ws.org/Vol-3739/abstract-18.pdf},
volume = 3739,
year = 2024
}
@inproceedings{llmbasedhealthcarechatbots-telmed2024,
apice = {LlmBasedHealthcareChatbotsTelmed2024},
author = {Montagna, Sara and Aguzzi, Gianluca and Ferretti, Stefano and Pengo, Martino Francesco and Klopfenstein, Lorenz Cuno and Ungolo, Michelangelo and Magnini, Matteo},
booktitle = {2024 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)},
doi = {10.1109/PerComWorkshops59983.2024.10503257},
keywords = {large language model, medical chatbot, chronic disease management},
numpages = 6,
pages = {346--351},
title = {LLM-based Solutions for Healthcare Chatbots: a Comparative Analysis},
year = 2024
}
apice = {LlmBasedHealthcareChatbotsTelmed2024},
author = {Montagna, Sara and Aguzzi, Gianluca and Ferretti, Stefano and Pengo, Martino Francesco and Klopfenstein, Lorenz Cuno and Ungolo, Michelangelo and Magnini, Matteo},
booktitle = {2024 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)},
doi = {10.1109/PerComWorkshops59983.2024.10503257},
keywords = {large language model, medical chatbot, chronic disease management},
numpages = 6,
pages = {346--351},
title = {LLM-based Solutions for Healthcare Chatbots: a Comparative Analysis},
year = 2024
}
@inproceedings{fauci-aequitas2024,
apice = {FauciAequitas2024},
articleno = 8,
author = {Magnini, Matteo and Ciatto, Giovanni and Calegari, Roberta and Omicini, Andrea},
booktitle = {AEQUITAS 2024: Fairness and Bias in AI},
dblp = {conf/aequitas/MagniniCCO24},
editor = {Calegari, Roberta and Dignum, Virginia and O'Sullivan, Barry},
iris = {11585/995740},
keywords = {AI Fairness, FaUCI, in-processing, regularization, mitigation},
month = oct,
note = {Proceedings of the 2nd Workshop on Fairness and Bias in AI co-located with 27th European Conference on Artificial Intelligence (ECAI 2024)},
numpages = 13,
pages = {1--13},
publisher = {CEUR-WS},
scholar = {12743200180573703475},
scopus = {2-s2.0-85210042328},
series = {CEUR Workshop Proceedings},
title = {Enforcing Fairness via Constraint Injection with {FaUCI}},
url = {https://ceur-ws.org/Vol-3808/paper8.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-3808/paper8.pdf},
urlpdf = {https://ceur-ws.org/Vol-3808/paper8.pdf},
volume = 3808,
wos = {WOS:001752291200008},
year = 2024
}
apice = {FauciAequitas2024},
articleno = 8,
author = {Magnini, Matteo and Ciatto, Giovanni and Calegari, Roberta and Omicini, Andrea},
booktitle = {AEQUITAS 2024: Fairness and Bias in AI},
dblp = {conf/aequitas/MagniniCCO24},
editor = {Calegari, Roberta and Dignum, Virginia and O'Sullivan, Barry},
iris = {11585/995740},
keywords = {AI Fairness, FaUCI, in-processing, regularization, mitigation},
month = oct,
note = {Proceedings of the 2nd Workshop on Fairness and Bias in AI co-located with 27th European Conference on Artificial Intelligence (ECAI 2024)},
numpages = 13,
pages = {1--13},
publisher = {CEUR-WS},
scholar = {12743200180573703475},
scopus = {2-s2.0-85210042328},
series = {CEUR Workshop Proceedings},
title = {Enforcing Fairness via Constraint Injection with {FaUCI}},
url = {https://ceur-ws.org/Vol-3808/paper8.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-3808/paper8.pdf},
urlpdf = {https://ceur-ws.org/Vol-3808/paper8.pdf},
volume = 3808,
wos = {WOS:001752291200008},
year = 2024
}
@inproceedings{skidatadegradation-woa2024,
apice = {SkidatadegradationWoa2024},
author = {Rafanelli, Andrea and Magnini, Matteo and Agiollo, Andrea and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {WOA 2024 -- 25th Workshop ``From Objects to Agents 2024''},
dblp = {conf/woa/RafanelliMACO24},
editor = {Alderighi, Marco and Baldoni, Matteo and Baroglio, Cristina and Micalizio, Roberto and Tedeschi, Stefano},
iris = {11585/975934},
issn = {1613-0073},
keywords = {Symbolic Knowledge Injection, Robustness, Neural Networks},
location = {Bard, AO, Italy},
month = jul,
numpages = 13,
pages = {20--32},
publisher = {Sun SITE Central Europe, RWTH Aachen University},
scholar = {9917174396528512749},
scopus = {2-s2.0-85200118300},
series = {CEUR Workshop Proceedings},
subseries = {AIxIA Series},
title = {An Empirical Study on the Robustness of Knowledge Injection Techniques Against Data Degradation},
url = {https://ceur-ws.org/Vol-3735/paper_02.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-3735/paper_02.pdf},
urlpdf = {https://ceur-ws.org/Vol-3735/paper_02.pdf},
volume = 3735,
wos = {WOS:001788634000002},
year = 2024
}
apice = {SkidatadegradationWoa2024},
author = {Rafanelli, Andrea and Magnini, Matteo and Agiollo, Andrea and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {WOA 2024 -- 25th Workshop ``From Objects to Agents 2024''},
dblp = {conf/woa/RafanelliMACO24},
editor = {Alderighi, Marco and Baldoni, Matteo and Baroglio, Cristina and Micalizio, Roberto and Tedeschi, Stefano},
iris = {11585/975934},
issn = {1613-0073},
keywords = {Symbolic Knowledge Injection, Robustness, Neural Networks},
location = {Bard, AO, Italy},
month = jul,
numpages = 13,
pages = {20--32},
publisher = {Sun SITE Central Europe, RWTH Aachen University},
scholar = {9917174396528512749},
scopus = {2-s2.0-85200118300},
series = {CEUR Workshop Proceedings},
subseries = {AIxIA Series},
title = {An Empirical Study on the Robustness of Knowledge Injection Techniques Against Data Degradation},
url = {https://ceur-ws.org/Vol-3735/paper_02.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-3735/paper_02.pdf},
urlpdf = {https://ceur-ws.org/Vol-3735/paper_02.pdf},
volume = 3735,
wos = {WOS:001788634000002},
year = 2024
}
@incollection{explanationprotocol-extraamas2023,
apice = {ExplanationProtocolExtraamas2023},
author = {Ciatto, Giovanni and Magnini, Matteo and Bezcu, Berk and Aydoǧan, Reyhan and Omicini, Andrea},
booktitle = {Explainable and Transparent {AI} and Multi-Agent Systems},
chapter = 3,
dblp = {conf/extraamas/CiattoMBAO23},
doi = {10.1007/978-3-031-40878-6_3},
editor = {Calvaresi, Davide and Najjar, Amro and Omicini, Andrea and Aydoǧan, Reyhan and Carli, Rachele and Ciatto, Giovanni and Mualla, Yazan and Främling, Kary},
iris = {11585/940656},
isbn = {978-3-031-40878-6},
issn = {0302-9743},
keywords = {XAI, recommender systems, multi-agent systems, explanation protocols, Spade, PyXMas},
lens = {148-308-040-946-924},
month = sep,
numpages = 21,
openalex = {W4386412605},
pages = {38--58},
publisher = {Springer},
scholar = {5371175139312621961},
scopus = {2-s2.0-85172214167},
semanticscholar = {261894587},
series = {Lecture Notes in Computer Science},
subseries = {Lecture Notes in Artificial Intelligence},
title = {A General-Purpose Protocol for Multi-Agent based Explanations},
url = {http://link.springer.com/10.1007/978-3-031-40878-6_3},
volume = 14127,
year = 2023
}
apice = {ExplanationProtocolExtraamas2023},
author = {Ciatto, Giovanni and Magnini, Matteo and Bezcu, Berk and Aydoǧan, Reyhan and Omicini, Andrea},
booktitle = {Explainable and Transparent {AI} and Multi-Agent Systems},
chapter = 3,
dblp = {conf/extraamas/CiattoMBAO23},
doi = {10.1007/978-3-031-40878-6_3},
editor = {Calvaresi, Davide and Najjar, Amro and Omicini, Andrea and Aydoǧan, Reyhan and Carli, Rachele and Ciatto, Giovanni and Mualla, Yazan and Främling, Kary},
iris = {11585/940656},
isbn = {978-3-031-40878-6},
issn = {0302-9743},
keywords = {XAI, recommender systems, multi-agent systems, explanation protocols, Spade, PyXMas},
lens = {148-308-040-946-924},
month = sep,
numpages = 21,
openalex = {W4386412605},
pages = {38--58},
publisher = {Springer},
scholar = {5371175139312621961},
scopus = {2-s2.0-85172214167},
semanticscholar = {261894587},
series = {Lecture Notes in Computer Science},
subseries = {Lecture Notes in Artificial Intelligence},
title = {A General-Purpose Protocol for Multi-Agent based Explanations},
url = {http://link.springer.com/10.1007/978-3-031-40878-6_3},
volume = 14127,
year = 2023
}
@inproceedings{ctl-aixia2022,
address = {Aachen, Germany},
apice = {CtlAixia2022},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {AIxIA 2022 Discussion Papers},
chapter = 2,
dblp = {conf/aiia/MagniniCO22},
editor = {Dovier, Agostino and Montanari, Angelo and Orlandini, Andrea},
iris = {11585/933657},
issn = {1613-0073},
keywords = {transfer learning; multi-agent systems; artificial general intelligence; symbolic knowledge extraction; symbolic knowledge injection},
location = {Udine, Italy},
month = jun,
note = {Proceedings of the Discussion Papers -- 21st International Conference of the Italian Association for Artificial Intelligence (AIxIA 2022 DP), co-located with 21st International Conference of the Italian Association for Artificial Intelligence (AIxIA 2022) -- Udine, Italy, November 28--December 2, 2022},
numpages = 11,
pages = {12--22},
publisher = {Sun SITE Central Europe, RWTH Aachen University},
scholar = {13606448051050829166},
scopus = {2-s2.0-85164132302},
series = {CEUR Workshop Proceedings},
subseries = {AIxIA Series},
title = {Bridging Symbolic and Sub-Symbolic {AI}: Towards Cooperative Transfer Learning in Multi-Agent Systems},
url = {https://ceur-ws.org/Vol-3419/paper2.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-3419/paper2.pdf},
urlpdf = {https://ceur-ws.org/Vol-3419/paper2.pdf},
volume = 3419,
year = 2023
}
address = {Aachen, Germany},
apice = {CtlAixia2022},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {AIxIA 2022 Discussion Papers},
chapter = 2,
dblp = {conf/aiia/MagniniCO22},
editor = {Dovier, Agostino and Montanari, Angelo and Orlandini, Andrea},
iris = {11585/933657},
issn = {1613-0073},
keywords = {transfer learning; multi-agent systems; artificial general intelligence; symbolic knowledge extraction; symbolic knowledge injection},
location = {Udine, Italy},
month = jun,
note = {Proceedings of the Discussion Papers -- 21st International Conference of the Italian Association for Artificial Intelligence (AIxIA 2022 DP), co-located with 21st International Conference of the Italian Association for Artificial Intelligence (AIxIA 2022) -- Udine, Italy, November 28--December 2, 2022},
numpages = 11,
pages = {12--22},
publisher = {Sun SITE Central Europe, RWTH Aachen University},
scholar = {13606448051050829166},
scopus = {2-s2.0-85164132302},
series = {CEUR Workshop Proceedings},
subseries = {AIxIA Series},
title = {Bridging Symbolic and Sub-Symbolic {AI}: Towards Cooperative Transfer Learning in Multi-Agent Systems},
url = {https://ceur-ws.org/Vol-3419/paper2.pdf},
urlopenaccess = {https://ceur-ws.org/Vol-3419/paper2.pdf},
urlpdf = {https://ceur-ws.org/Vol-3419/paper2.pdf},
volume = 3419,
year = 2023
}
@incollection{kill-woa2022,
apice = {KillWoa2022},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {WOA 2022 -- 23rd Workshop ``From Objects to Agents''},
dblp = {conf/woa/MagniniCO22},
editor = {Ferrando, Angelo and Mascardi, Viviana},
iris = {11585/899373},
issn = {1613-0073},
keywords = {symbolic knowledge injection; AI; ML; neural networks; KILL; PSyKI},
month = nov,
numpages = 16,
pages = {61--76},
publisher = {Sun SITE Central Europe, RWTH Aachen University},
scholar = {514437633827732665},
scopus = {2-s2.0-85142481549},
semanticscholar = {253270036},
series = {CEUR Workshop Proceedings},
subseries = {AIxIA Series},
title = {A view to a {KILL}: Knowledge Injection via Lambda Layer},
url = {http://ceur-ws.org/Vol-3261/paper5.pdf},
urlopenaccess = {http://ceur-ws.org/Vol-3261/paper5.pdf},
urlpdf = {http://ceur-ws.org/Vol-3261/paper5.pdf},
volume = 3261,
wos = {WOS:001788658400005},
year = 2022
}
apice = {KillWoa2022},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {WOA 2022 -- 23rd Workshop ``From Objects to Agents''},
dblp = {conf/woa/MagniniCO22},
editor = {Ferrando, Angelo and Mascardi, Viviana},
iris = {11585/899373},
issn = {1613-0073},
keywords = {symbolic knowledge injection; AI; ML; neural networks; KILL; PSyKI},
month = nov,
numpages = 16,
pages = {61--76},
publisher = {Sun SITE Central Europe, RWTH Aachen University},
scholar = {514437633827732665},
scopus = {2-s2.0-85142481549},
semanticscholar = {253270036},
series = {CEUR Workshop Proceedings},
subseries = {AIxIA Series},
title = {A view to a {KILL}: Knowledge Injection via Lambda Layer},
url = {http://ceur-ws.org/Vol-3261/paper5.pdf},
urlopenaccess = {http://ceur-ws.org/Vol-3261/paper5.pdf},
urlpdf = {http://ceur-ws.org/Vol-3261/paper5.pdf},
volume = 3261,
wos = {WOS:001788658400005},
year = 2022
}
@inproceedings{kins-cilc2022,
apice = {KinsCilc2022},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {CILC 2022 -- Italian Conference on Computational Logic},
dblp = {conf/cilc/MagniniCO22},
editor = {Calegari, Roberta and Ciatto, Giovanni and Omicini, Andrea},
iris = {11585/899494},
issn = {1613-0073},
keywords = {neural network; explainable AI; symbolic knowledge injection; KINS; PSyKI},
location = {Bologna, Italy},
numpages = 14,
pages = {254--267},
publisher = {CEUR-WS},
scholar = {10469078385425944401},
scopus = {2-s2.0-85138240764},
series = {CEUR Workshop Proceedings},
subseries = {AI*IA Series},
title = {{KINS}: Knowledge Injection via Network Structuring},
url = {http://ceur-ws.org/Vol-3204/paper_25.pdf},
urlopenaccess = {http://ceur-ws.org/Vol-3204/paper_25.pdf},
urlpdf = {http://ceur-ws.org/Vol-3204/paper_25.pdf},
volume = 3204,
wos = {WOS:001798558900019},
year = 2022
}
apice = {KinsCilc2022},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {CILC 2022 -- Italian Conference on Computational Logic},
dblp = {conf/cilc/MagniniCO22},
editor = {Calegari, Roberta and Ciatto, Giovanni and Omicini, Andrea},
iris = {11585/899494},
issn = {1613-0073},
keywords = {neural network; explainable AI; symbolic knowledge injection; KINS; PSyKI},
location = {Bologna, Italy},
numpages = 14,
pages = {254--267},
publisher = {CEUR-WS},
scholar = {10469078385425944401},
scopus = {2-s2.0-85138240764},
series = {CEUR Workshop Proceedings},
subseries = {AI*IA Series},
title = {{KINS}: Knowledge Injection via Network Structuring},
url = {http://ceur-ws.org/Vol-3204/paper_25.pdf},
urlopenaccess = {http://ceur-ws.org/Vol-3204/paper_25.pdf},
urlpdf = {http://ceur-ws.org/Vol-3204/paper_25.pdf},
volume = 3204,
wos = {WOS:001798558900019},
year = 2022
}
@incollection{psyki-extraamas2022,
apice = {PsykiExtraamas2022},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {Explainable and Transparent AI and Multi-Agent Systems},
chapter = 6,
dblp = {conf/atal/MagniniCO22},
doi = {10.1007/978-3-031-15565-9_6},
editor = {Calvaresi, Davide and Najjar, Amro and Winikoff, Michael and Främling, Kary},
eisbn = {978-3-031-15565-9},
eissn = {1611-3349},
iris = {11585/899511},
isbn = {978-3-031-15564-2},
issn = {0302-9743},
keywords = {Symbolic Knowledge Injection, Explainable AI, XAI, Neural Networks, PSyKI},
lens = {001-522-718-541-434},
note = {4th International Workshop, EXTRAAMAS 2022, Virtual Event, May 9--10, 2022, Revised Selected Papers},
openalex = {W4297897134},
pages = {90--108},
publisher = {Springer},
scholar = {7587528289517313138},
scopus = {2-s2.0-85138317005},
semanticscholar = {252545848},
series = {Lecture Notes in Computer Science},
title = {On the Design of {PSyKI}: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors},
url = {https://link.springer.com/chapter/10.1007/978-3-031-15565-9_6},
urlpdf = {https://link.springer.com/content/pdf/10.1007/978-3-031-15565-9_6.pdf},
volume = 13283,
wos = {WOS:000870042100006},
year = 2022
}
apice = {PsykiExtraamas2022},
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {Explainable and Transparent AI and Multi-Agent Systems},
chapter = 6,
dblp = {conf/atal/MagniniCO22},
doi = {10.1007/978-3-031-15565-9_6},
editor = {Calvaresi, Davide and Najjar, Amro and Winikoff, Michael and Främling, Kary},
eisbn = {978-3-031-15565-9},
eissn = {1611-3349},
iris = {11585/899511},
isbn = {978-3-031-15564-2},
issn = {0302-9743},
keywords = {Symbolic Knowledge Injection, Explainable AI, XAI, Neural Networks, PSyKI},
lens = {001-522-718-541-434},
note = {4th International Workshop, EXTRAAMAS 2022, Virtual Event, May 9--10, 2022, Revised Selected Papers},
openalex = {W4297897134},
pages = {90--108},
publisher = {Springer},
scholar = {7587528289517313138},
scopus = {2-s2.0-85138317005},
semanticscholar = {252545848},
series = {Lecture Notes in Computer Science},
title = {On the Design of {PSyKI}: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors},
url = {https://link.springer.com/chapter/10.1007/978-3-031-15565-9_6},
urlpdf = {https://link.springer.com/content/pdf/10.1007/978-3-031-15565-9_6.pdf},
volume = 13283,
wos = {WOS:000870042100006},
year = 2022
}
@incollection{neurosymbolic-woa25y,
address = {Cham},
apice = {NeurosymbolicWoa25Y},
author = {Agiollo, Andrea and Calegari, Roberta and Ciatto, Giovanni and Magnini, Matteo and Omicini, Andrea and Sabbatini, Federico},
booktitle = {The Agents Journey: Twenty-Five Years of Multi-agent Systems},
chapter = 12,
doi = {10.1007/978-3-032-22940-3_12},
editor = {Mascardi, Viviana and Omicini, Andrea},
eisbn = {978-3-032-22940-3},
eissn = {1611-3349},
iris = {11585/1061411},
isbn = {978-3-032-22939-7},
issn = {0302-9743},
keywords = {Rational Agents, Logic Programming, Multi-agent Systems, Symbolic-Subsymbolic Integration},
lens = {028-851-073-271-306},
month = apr,
numpages = 20,
openalex = {W7155969644},
pages = {320--339},
publisher = {Springer Nature Switzerland},
scholar = {21797340038813643},
scopus = {2-s2.0-105041239279},
series = {Lecture Notes in Computer Science},
subseries = {State-of-the-Art Survey},
title = {Intelligent Agents from Symbolic to Neurosymbolic Systems: The Quest for Integration},
url = {https://link.springer.com/10.1007/978-3-032-22940-3_12},
urlopenaccess = {https://link.springer.com/content/pdf/10.1007/978-3-032-22940-3_12.pdf},
volume = 16395,
year = 2026
}
address = {Cham},
apice = {NeurosymbolicWoa25Y},
author = {Agiollo, Andrea and Calegari, Roberta and Ciatto, Giovanni and Magnini, Matteo and Omicini, Andrea and Sabbatini, Federico},
booktitle = {The Agents Journey: Twenty-Five Years of Multi-agent Systems},
chapter = 12,
doi = {10.1007/978-3-032-22940-3_12},
editor = {Mascardi, Viviana and Omicini, Andrea},
eisbn = {978-3-032-22940-3},
eissn = {1611-3349},
iris = {11585/1061411},
isbn = {978-3-032-22939-7},
issn = {0302-9743},
keywords = {Rational Agents, Logic Programming, Multi-agent Systems, Symbolic-Subsymbolic Integration},
lens = {028-851-073-271-306},
month = apr,
numpages = 20,
openalex = {W7155969644},
pages = {320--339},
publisher = {Springer Nature Switzerland},
scholar = {21797340038813643},
scopus = {2-s2.0-105041239279},
series = {Lecture Notes in Computer Science},
subseries = {State-of-the-Art Survey},
title = {Intelligent Agents from Symbolic to Neurosymbolic Systems: The Quest for Integration},
url = {https://link.springer.com/10.1007/978-3-032-22940-3_12},
urlopenaccess = {https://link.springer.com/content/pdf/10.1007/978-3-032-22940-3_12.pdf},
volume = 16395,
year = 2026
}
0000-0001-9990-420X