Lucio La Cava, Ph.D.

Contact me at:

lucio [dot] lacava [at] dimes [dot] unical [dot] it

I am an Assistant Professor (RTD-A) at the Department of Computer Engineering, Modeling, Electronics, and Systems Engineering (DIMES) of the University of Calabria, Italy. Previously, I got a Ph.D. cum laude in Information and Communication Technologies at the DIMES Department of the University of Calabria, with a thesis on “Graph Mining and Multimodal Representation Learning for Decentralized Socio-Economic Domains.”

I graduated magna cum laude in Computer Engineering in 2020 at the University of Calabria. I was visiting researcher at the IT University of Copenhagen from August to September 2025, and visiting Ph.D. student from January to April 2023, working in the NEtwoRks, Data, and Society (NERDS) group. I am a member of the Machine Learning, NLP and Network Science Team @Artificial Intelligence and Data Science Lab at DIMES, and junior fellow of the Complex Human Behavior Lab (CHuB) @Fondazione Bruno Kessler (FBK).

I’m interested in Natural Language Processing (w/ particular focus on Large Language Models), Multimodal Representation Learning (including Graph Representation Learning and Computer Vision) and Graph Mining.

news

Aug 21, 2025	🇩🇰 Flying to Copenhagen for visiting the NERDS team at ITU, working on the COCOONS project with Luca Maria Aiello!
Aug 20, 2025	🥳 Paper accepted with EMNLP 2025 Main Conference!
Aug 4, 2025	🥳 Resource paper accepted with CIKM 2025!
Aug 3, 2025	📝 New preprint out on Authorship Attribution in Multilingual Machine-Generated Texts 🤖 🔍
Jul 27, 2025	🇦🇹 Flying to Vienna for presenting our paper on the LLMs’ ability to spontaneously and conditionally modify moral expressions through text manipulation!
Jun 23, 2025	🇩🇰 Flying to Copenaghen for chairing our Workshop on Next Generation and Alternative Social Media @ ICWSM 2025!
Jun 16, 2025	🇮🇹 Traveling to Ischia for the Italian Symposium On Advanced Database Systems!
May 31, 2025	🥳 Paper accepted with Online Social Networks and Media!
May 20, 2025	🇸🇪 Flying to Uppsala for visiting at the UU-Infolab, where I’ll give a PhD-level course on Large Language Models!
May 20, 2025	🥳 Paper accepted with Pervasive and Mobile Computing!
May 15, 2025	🥳 Paper accepted with ACL 2025 Main Conference!
Apr 15, 2025	📝 New preprint out with a novel benchmark for machine-generated text detection and attribution 🤖 🔍
Mar 15, 2025	🥳 Paper accepted with Social Network Analysis and Mining!
Feb 24, 2025	🇺🇸 Flying to Philadelphia for presenting our paper on mimicking human personalities via LLMs!
Feb 6, 2025	🎙️ Gave a talk for the NetPLACE seminar series! 🔥
Jan 29, 2025	📝 New preprint out on Mixture of Experts for Link Prediction in Multilayer Networks!
Dec 10, 2024	🎉 Paper accepted with AAAI 2025 (acceptance rate 23.4%)
Nov 11, 2024	🇺🇸 Flying to Miami for presenting our paper on the limits of LLMs in lexical entailment recognition!
Oct 18, 2024	🇪🇸 Flying to Santiago de Compostela for presenting our paper on the detection and attribution of AI-generated text!
Sep 20, 2024	🥳 Paper accepted with EMNLP 2024 Findings!
Sep 16, 2024	📝 New preprint out on safeguarding (decentralized) social media through LLM agents for automatic rule compliance checking 🤖 🔍
Jul 4, 2024	🥳 Paper accepted with ECAI 2024 (acceptance rate 23%)
Jul 3, 2024	📝 New preprint out on hidden swing voters’ vulnerability to propaganda techniques during the 2022 Italian general elections 🗳️ 🇮🇹
Jun 21, 2024	📝 New preprint out on the limits of LLMs in lexical entailment recognition 🔬
Jun 3, 2024	🇺🇸 Flying to Buffalo for chairing our 1st International Workshop on Decentralizing the Web (DeWeb’24) @ ICWSM!
May 21, 2024	🇩🇪 Off to Stuttgart for presenting a tutorial and two papers on Decentralized Online Social Networks at WebSci’24! (Update: 🏆 Our paper “Polarization in Decentralized Online Social Networks” got the best short-paper award!)
May 2, 2024	I am so excited to share that my journey with the University of Calabria continues as an Assistant Professor starting today! 👨🏻‍💻 Looking forward to the adventures ahead! ✨
Feb 27, 2024	🎓👨🏻‍💻 Successfully defended (cum laude ✨) my Ph.D. dissertation “Graph Mining and Multimodal Representation Learning for Emerging Decentralized Socio-Economic Domains” 🥳
Jan 15, 2024	🧠 New preprint out on Artificial Agents mirroring human personalities through Open Large Language Models (LLMs)
Dec 7, 2023	🥳 Our paper on the Twitter migration to Mastodon is out now on ScientificReports!
Nov 6, 2023	🔬 Presenting my tutorial on Mastodon at ASONAM 2023 in Kusadasi, Turkey 🇹🇷 (Update: 🏆 the tutorial has been awarded for being inspiring!)
Oct 3, 2023	🔥 The NFT-70M dataset is here!
Aug 28, 2023	📚 Flying to Greece for the Google DeepMind Mediterranean Machine Learning Summer School (M2L) in Thessaloniki 🇬🇷 (Update: 🏆 I won the AEGEAN Scholarship as one of the top students!)
Jul 24, 2023	💻 (Virtually) Presenting our new tool at the ACM SIGIR 2023
Jul 19, 2023	🇩🇰 Flying to Copenhagen for presenting our work on the #TwitterMigration to Mastodon 🐘 at IC2S2 2023
May 2, 2023	🇺🇸 Off to Austin for presenting our work at TheWebConf2023 (Update: 🏆 I won a Student Travel Award sponsored by Zhipu AI!)
Apr 1, 2023	🥳 Paper accepted with ACM SIGIR 2023!
Jan 25, 2023	🥳 Paper accepted with The ACM Web Conference 2023! (acceptance rate 19.2%)
Jan 7, 2023	🚀🇩🇰 I have joined the NERDS team at ITU as a visiting PhD Student, working on the COCOONS project under the supervision of Luca Maria Aiello. It is going to be a fascinating experience! 👨🏻‍💻

selected publications

OpenTuringBench: An Open-Model-based Benchmark and Framework for Machine-Generated Text Detection and Attribution

Lucio La Cava, and Andrea Tagarelli

Accepted with EMNLP 2025 (Main Conference), Aug 2025

arXiv Bib

@article{LaCava2025otb,
  title = {OpenTuringBench: An Open-Model-based Benchmark and Framework for Machine-Generated Text Detection and Attribution},
  journal = {Accepted with EMNLP 2025 (Main Conference)},
  author = {La Cava, Lucio and Tagarelli, Andrea},
  year = {2025},
  month = aug,
  bibtex_show = true,
  selected = true
}

Authorship Attribution in Multilingual Machine-Generated Texts

Lucio La Cava, Dominik Macko, Róbert Móro, and 2 more authors

arXiv preprint arXiv:2508.01656, Aug 2025

arXiv Bib

@article{LaCava2025mAA,
  title = {Authorship Attribution in Multilingual Machine-Generated Texts},
  journal = {arXiv preprint arXiv:2508.01656},
  author = {La Cava, Lucio and Macko, Dominik and Móro, Róbert and Srba, Ivan and Tagarelli, Andrea},
  year = {2025},
  month = aug,
  bibtex_show = true,
  selected = true
}

Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text Manipulation

Candida Maria Greco, Lucio La Cava, Lorenzo Zangari, and 1 more author

ACL 2025 (Main Conference), Jul 2025

arXiv Bib

@article{Greco2025morality,
  title = {Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text Manipulation},
  journal = {ACL 2025 (Main Conference)},
  author = {Greco, Candida Maria and La Cava, Lucio and Zangari, Lorenzo and Tagarelli, Andrea},
  year = {2025},
  month = jul,
  bibtex_show = true,
  selected = true
}

Safeguarding Decentralized Social Media: LLM Agents for Automating Community Rule Compliance

Lucio La Cava, and Andrea Tagarelli

Online Social Networks and Media, May 2025

Bib HTML

@article{LaCava2024safeguarding,
  title = {Safeguarding Decentralized Social Media: LLM Agents for Automating Community Rule Compliance},
  author = {La Cava, Lucio and Tagarelli, Andrea},
  journal = {Online Social Networks and Media},
  month = may,
  year = {2025},
  doi = {10.1016/j.osnem.2025.100319},
  bibtex_show = true,
  selected = true
}

Heuristic-Informed Mixture of Experts for Link Prediction in Multilayer Networks

Lucio La Cava, Domenico Mandaglio, Lorenzo Zangari, and 1 more author

arXiv preprint arXiv:2501.17557, Jan 2025

arXiv Bib

@article{lacava2025mlmoe,
  title = {Heuristic-Informed Mixture of Experts for Link Prediction in Multilayer Networks},
  author = {La Cava, Lucio and Mandaglio, Domenico and Zangari, Lorenzo and Tagarelli, Andrea},
  journal = {arXiv preprint arXiv:2501.17557},
  year = {2025},
  month = jan,
  bibtex_show = true,
  selected = true
}

Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models

Lucio La Cava, and Andrea Tagarelli

Proceedings of the AAAI Conference on Artificial Intelligence, Apr 2025

Abs Bib HTML

The emergence of unveiling human-like behaviors in Large Language Models (LLMs) has led to a closer connection between NLP and human psychology. However, research on the personalities exhibited by LLMs has largely been confined to limited investigations using individual psychological tests, primarily focusing on a small number of commercially licensed LLMs. This approach overlooks the extensive use and significant advancements observed in open-source LLMs. This work aims to address both the above limitations by conducting an in-depth investigation of a significant body of 12 LLM Agents based on the most representative Open models, through the two most well-known psychological assessment tests, namely Myers-Briggs Type Indicator (MBTI) and Big Five Inventory (BFI). Our approach involves evaluating the intrinsic personality traits of LLM agents and determining the extent to which these agents can mimic human personalities when conditioned by specific personalities and roles. Our findings unveil that (i) each LLM agent showcases distinct human personalities; (ii) personality-conditioned prompting produces varying effects on the agents, with only few successfully mirroring the imposed personality, while most of them being “closed-minded’’ (i.e., they retain their intrinsic traits); and (iii) combining role and personality conditioning can enhance the agents’ ability to mimic human personalities. Our work represents a step up in understanding the dense relationship between NLP and human psychology through the lens of LLMs.
@article{LaCava2024agentspersonalities, title = {Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models}, volume = {39}, doi = {10.1609/aaai.v39i2.32125}, number = {2}, journal = {Proceedings of the AAAI Conference on Artificial Intelligence}, author = {La Cava, Lucio and Tagarelli, Andrea}, year = {2025}, month = apr, pages = {1355-1363}, bibtex_show = true, selected = true }

Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Text

Lucio La Cava, Davide Costa, and Andrea Tagarelli

In ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, Oct 2024

Bib HTML

@inproceedings{LaCava2024AIdetection,
  author = {La Cava, Lucio and Costa, Davide and Tagarelli, Andrea},
  title = {Is Contrasting All You Need? Contrastive Learning for the Detection
                    and Attribution of AI-generated Text},
  booktitle = {{ECAI} 2024 - 27th European Conference on Artificial Intelligence,
                    19-24 October 2024, Santiago de Compostela, Spain},
  series = {Frontiers in Artificial Intelligence and Applications},
  volume = {392},
  pages = {3179--3186},
  publisher = {{IOS} Press},
  month = oct,
  year = {2024},
  doi = {10.3233/FAIA240862},
  bibtex_show = true,
  selected = true
}