Lucio La Cava

@luciolcw.bsky.social

Assistant Professor @ University of Calabria ๐Ÿ‡ฎ๐Ÿ‡น ๐Ÿ‘จ๐Ÿปโ€๐Ÿ’ป Ph.D. in Information and Communication Technologies Prev. Visiting @ IT University of Copenhagen ๐Ÿ‡ฉ๐Ÿ‡ฐ ๐Ÿค– Multimodal Representation Learning & Networks https://luciolacava.me/

๐ŸŽ‰ Happy to share that our work โ€œAuthorship Attribution in Multilingual Machine-Generated Textsโ€ has been accepted to #ACL2026 (Main)! ๐Ÿง Can you tell if a text was written by a human or a specific LLM? Now imagine doing it across 18 languages! ๐Ÿ“„ arxiv.org/abs/2508.01656

Authorship Attribution in Multilingual Machine-Generated Texts

As Large Language Models (LLMs) have reached human-like fluency and coherence, distinguishing machine-generated text (MGT) from human-written content becomes increasingly difficult. While early effort...

arxiv.org

๐Ÿง  ๐Ÿ•ต๏ธ LLMs are mastering the "imitation game"... but can we still tell who wrote what? ๐Ÿ“ At #EMNLP2025, we present OpenTuringBench โ€” 500K+ texts, 7 open LLMs, 7 challenging tasks, and a new method for machine-generated text detection and attribution! ๐Ÿ“ Today at 2 PM in Hall C

Bild

๐Ÿค– Do LLMs reflect our moral expressionsโ€”or alter them? In our #ACL2025 paper, we study 12 widely used LLMs and found that moral expressions are altered to varying degrees depending on the editing task and moral conditioning prompt. ๐Ÿ“ ACL2025 โ€” Hall X5 (28) ๐Ÿ•š Today, 11:00โ€“12:30

Bild

This week we had the pleasure to host our colleagues and friends from Universitร  della Calabria. @luciolcw.bsky.social delivered a well-attended intensive course on Large Language Models, and Andrea Tagarelli presented the research done by his team. We look forward to new collaborations.

BildBildBild

Yesterday, we had the pleasure of e-meeting the OpenAI team for an insightful discussion about Open LLMs. While I canโ€™t share details just yet, thereโ€™s a lot to be excited about! ๐Ÿš€ It was particularly inspiring to see Sam Altman join the session and share OpenAIโ€™s vision for open models ๐Ÿคฏ

Bild

๐Ÿšจ Just 1 week to go! โณ Don't miss your chance to submit short papers and 2-page abstracts to the Next-Gen and Alternative Social Media Workshop at @icwsm.bsky.social โ€” deadline is April 14 (AoE)! โฐ ๐Ÿ‘‰๐Ÿผ nextgensocial-workshop.github.io

Lucio La Cava@luciolcw.bsky.social ยท last yr.

๐Ÿšจ Deadline extended to April 14 ๐Ÿ“… ๐Ÿ“š Extra time to submit your abstracts and short papers to the Next-Gen and Alternative Social Media Workshop at @icwsm.bsky.social! ๐Ÿ‘‰๐Ÿผ nextgensocial-workshop.github.io

๐Ÿšจ Deadline extended to April 14 ๐Ÿ“… ๐Ÿ“š Extra time to submit your abstracts and short papers to the Next-Gen and Alternative Social Media Workshop at @icwsm.bsky.social! ๐Ÿ‘‰๐Ÿผ nextgensocial-workshop.github.io

Lucio La Cava@luciolcw.bsky.social ยท last yr.

๐Ÿ”ฅ Are you working on next-gen or alternative social media platforms like #Bluesky or #Mastodon? ๐Ÿ‘‡๐Ÿป This @icwsm.bsky.social workshop is for you! ๐Ÿ˜Ž ๐Ÿ“ข nextgensocial-workshop.github.io ๐Ÿ“š We solicit research, position, demo, and dataset paper submissions! ๐Ÿ“† Submissions: March 31, 2025

๐ŸŽ‰ Exciting news! Our paper "Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models" has been accepted at the 39th Annual AAAI Conference on Artificial Intelligence #AAAI2025! ๐Ÿฅณ ๐Ÿ“ Check it out here: arxiv.org/abs/2401.07115 #NLP

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

The emergence of unveiling human-like behaviors in Large Language Models (LLMs) has led to a closer connection between NLP and human psychology. Scholars have been studying the inherent personalities ...

arxiv.org

๐Ÿ‘จ๐Ÿปโ€๐Ÿ’ป Glad to have presented our work "Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Text" ๐Ÿค– at ECAI 2024 in Santiago de Compostela ๐Ÿ‡ช๐Ÿ‡ธ ๐Ÿ“š doi.org/10.3233/FAIA... We also walked the final section of the Santiagoโ€™s French Way! โœจ

BildBildBildBild

๐Ÿšจ Can you really spot if a text is AI-generated, and pinpoint which LLM created it? ๐Ÿ“๐Ÿค– ๐Ÿ“ข Check out our new work "Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Text" โ€” just accepted at ECAI2024 ๐Ÿฅณ ๐Ÿ‘‰๐Ÿผ arxiv.org/abs/2407.09364

Bild

I am so excited to share that my journey with the University of Calabria continues as an Assistant Professor starting today! ๐Ÿ‘จ๐Ÿปโ€๐Ÿ’ป Looking forward to the adventures ahead! โœจ

๐Ÿ“ข Exciting news for DeWeb 2024! ๐Ÿš€ We're glad to announce that Andy Piper (Developer Relations @ Mastodon ๐Ÿ˜) will be the keynote speaker at the 1st Workshop on Decentralizing the Web at ICWSM'24 ๐Ÿš€ ๐Ÿ—“๏ธ Abstracts and short papers are due by April 5! ๐Ÿ‘‰๐Ÿผ deweb-workshop.github.io

Bild

๐Ÿšจ Deadline extended to April 5 ๐Ÿšจ ๐Ÿ“š Extra time to submit your abstracts and short papers to the 1st Workshop on Decentralizing the Web at ICWSM'24 ๐Ÿ“ Join us and collaborate to draft a white paper on the opportunities and challenges within the DeWeb! ๐Ÿ‘‰๐Ÿผ deweb-workshop.github.io

Bild