Structured Machine Learning Group

Structured Machine Learning Group

Welcome to the website of the Structured Machine Learning Group at the University of Trento, Italy.

The SML group carries out research on different topics of theoretical and applied Machine Learning, with a focus on domains characterized by complex structures like sequences, trees, graphs and relational knowledge bases. Our main research activities involve combining statistical and symbolic approaches to learning, by integrating logic and constraint programming with statistical learning approaches. Active areas include structured-output prediction, learning to optimize, reasoning and learning in hybrid domains, constructive preference elicitation and bioinformatics applications. See here for more details on our research.


Recent Publications


Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain Burcu Sayin, Pasquale Minervini, Jacopo Staiano, and Andrea Passerini. In Proceedings of the 6th Clinical Natural Language Processing Workshop, 2024.
@inproceedings {sayin2024LLMs,
    author = { Sayin, Burcu and Minervini, Pasquale and Staiano, Jacopo and Passerini, Andrea },
    title = "Can {LLM}s Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain",
    booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
    month = "June",
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.clinicalnlp-1.19",
    doi = "10.18653/v1/2024.clinicalnlp-1.19",
    pages = "218--237",
}
A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts Samuele Bortolotti, Emanuele Marconato, Tommaso Carraro, Paolo Morettin, Emile Krieken, Antonio Vergari, Stefano Teso, and Andrea Passerini. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2024.
@inproceedings {bortolotti2024benchmark,
    author = { Bortolotti, Samuele and Marconato, Emanuele and Carraro, Tommaso and Morettin, Paolo and van Krieken, Emile and Vergari, Antonio and Teso, Stefano and Passerini, Andrea },
    title = "A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts",
    booktitle = "The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track",
    year = "2024",
    url = "https://openreview.net/forum?id=5VtI484yVy",
    code = "https://github.com/unitn-sml/rsbench-code",
}
BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts Emanuele Marconato, Samuele Bortolotti, Emile Krieken, Antonio Vergari, Andrea Passerini, and Stefano Teso. In The 40th Conference on Uncertainty in Artificial Intelligence, 2024.
@inproceedings {marconato2024bears,
    author = { Marconato, Emanuele and Bortolotti, Samuele and van Krieken, Emile and Vergari, Antonio and Passerini, Andrea and Teso, Stefano },
    title = "{BEARS} Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts",
    booktitle = "The 40th Conference on Uncertainty in Artificial Intelligence",
    year = "2024",
    code = "https://github.com/samuelebortolotti/bears",
    url = "https://openreview.net/forum?id=pDcM1k7mgZ",
}
Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph Marco Bronzini, Carlo Nicolini, Bruno Lepri, Jacopo Staiano, and Andrea Passerini. In First Conference on Language Modeling, 2024.
@inproceedings {bronziniunveiling,
    author = { Bronzini, Marco and Nicolini, Carlo and Lepri, Bruno and Staiano, Jacopo and Passerini, Andrea },
    title = "Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph",
    booktitle = "First Conference on Language Modeling",
    year = "2024",
    url = "https://openreview.net/forum?id=dWYRjT501w",
    code = "https://github.com/Ipazia-AI/latent-explorer",
}
Glitter or gold? Deriving structured insights from sustainability reports via large language models Marco Bronzini, Carlo Nicolini, Bruno Lepri, Andrea Passerini, and Jacopo Staiano. In EPJ Data Science 13(1), 2024.
@article {bronzini2024glitter,
    author = { Bronzini, Marco and Nicolini, Carlo and Lepri, Bruno and Passerini, Andrea and Staiano, Jacopo },
    title = "Glitter or gold? Deriving structured insights from sustainability reports via large language models",
    journal = "EPJ Data Science",
    volume = "13",
    number = "1",
    pages = "41",
    year = "2024",
    publisher = "Springer Berlin Heidelberg",
    url = "https://epjdatascience.springeropen.com/articles/10.1140/epjds/s13688-024-00481-2",
    code = "https://github.com/saturnMars/derivingStructuredInsightsFromSustainabilityReportsViaLargeLanguageModels",
}
Personalized Algorithmic Recourse with Preference Elicitation Giovanni De Toni, Paolo Viappiani, Stefano Teso, Bruno Lepri, and Andrea Passerini. In Transactions on Machine Learning Research, 2024.
@article {tmlr2024,
    author = { Toni, Giovanni De and Viappiani, Paolo and Teso, Stefano and Lepri, Bruno and Passerini, Andrea },
    title = "Personalized Algorithmic Recourse with Preference Elicitation",
    journal = "Transactions on Machine Learning Research",
    issn = "2835-8856",
    year = "2024",
    url = "https://openreview.net/forum?id=8sg2I9zXgO",
    note = "",
}
Enhancing SMT-based Weighted Model Integration by structure awareness Giuseppe Spallitta, Gabriele Masina, Paolo Morettin, Andrea Passerini, and Roberto Sebastiani. In Artificial Intelligence, 2024.
@article {aij2024,
    author = { Spallitta, Giuseppe and Masina, Gabriele and Morettin, Paolo and Passerini, Andrea and Sebastiani, Roberto },
    title = "Enhancing SMT-based Weighted Model Integration by structure awareness",
    journal = "Artificial Intelligence",
    volume = "328",
    pages = "104067",
    year = "2024",
    issn = "0004-3702",
    doi = "https://doi.org/10.1016/j.artint.2024.104067",
    url = "https://www.sciencedirect.com/science/article/pii/S0004370224000031",
    keywords = "Hybrid probabilistic inference, Weighted Model Integration, Satisfiability modulo theories",
}
Generating fine-grained surrogate temporal networks Antonio Longa, Giulia Cencetti, Sune Lehmann, Andrea Passerini, and Bruno Lepri. In Communications Physics 7(22), 2024.
@article {commphys2024,
    author = { Longa, Antonio and Cencetti, Giulia and Lehmann, Sune and Passerini, Andrea and Lepri, Bruno },
    title = "Generating fine-grained surrogate temporal networks",
    year = "2024",
    journal = "Communications Physics",
    volume = "7",
    number = "22",
    url = "https://arxiv.org/abs/2205.08820",
}
See complete publication list