September 24

08:30 – 09:30 Registration

09:30 – 12:30 Tutorial: Language-and-vision models: From Image-Language Alignment to Storytelling and Narration (Sandro Pezzelle, University of Amsterdam)

12:30 – 14:00 Lunch Break

14:00 – 14:30 Opening Session

14:30 – 15:30 Oral Presentations

• A Leaderboard for Benchmarking LLMs on Italian (Bernardo Magnini, Marco Madeddu, Michele Resta, Roberto Zanoli, Martin Cimmino, Paolo Albano and Viviana Patti)
• Sustainable Italian LLM Evaluation: Community Perspectives and Methodological Guidelines (Luca Moroni, Gianmarco Pappacoda, Edoardo Barba, Simone Conia, Andrea Galassi, Bernardo Magnini, Roberto Navigli, Paolo Torroni and Roberto Zanoli)
• BABILong-ITA: A New Benchmark for Testing Large Language Models Effective Context Length and a Context Extension Method (Fabio Tamburini)
• BAMBI Goes to School: Evaluating Italian BabyLMs with Invalsi-ITA (Luca Capone, Alice Suozzi, Gianluca Lebani and Alessandro Lenci)
• Evaluating Models, Prompting Strategies, and Task Formats: A Case Study on the MACID Challenge (Matteo Rinaldi, Rossella Varvara, Lorenzo Gregori and Andrea Amelio Ravelli)

15:30 – 16:30 Poster Session + Coffee Break

• MakeItSample: A Python Library for Generating Typological Language Samples Based on the Diversity Value Metric (Luca Brigada Villa)
• Building It-tok: An Italian TikTok Corpus (Luisa Troncone)
• Disinformation as Digital Mobilization: A Social Identity Approach to Multilingual Collective Action on Social Media (Lorella Viola)
• Do LLMs Authentically Represent Affective Experiences of People with Disabilities on Social Media?
  (Marco Bombieri, Simone Paolo Ponzetto and Marco Rospocher)
• Improving Reasoning beyond English through Structured Abstraction and Self-Refinement (Federico Ranaldi and Leonardo Ranaldi)
• Curated Data Does Not Mean Representative Data When Training Large Language Models: An Experiment Using Representative Data for Italian (Fabio Tamburini)
• Is It Still a Village? Tracing Grammaticalization with Word Embeddings (Joseph E. Larson and Patrícia Amaral)
• LLMike: Exploring Large Language Models’ Abilities in Wheel of Fortune Riddles (Ejdis Gjinika, Nicola Arici, Andrea Loreggia, Luca Putelli, Ivan Serina and Alfonso Emilio Gerevini)
• Classifying Gas Pipe Damage Descriptions in Low-Diversity Corpora (Luca Catalano, Federico D’Asaro, Michele Pantaleo, Prima Acharjee, Minal Jamshed, Nicola Giulietti, Eugenio Fossat and Giuseppe Rizzo)
• Benchmarking Historical Phase Recognition from Text and Events (Fabio Celli and Marco Rovera)
  Is Multimodality Still Required for Multimodal Machine Translation? A Case Study on English and Italian (Elio Musacchio, Lucia Siciliani, Pierpaolo Basile and Giovanni Semeraro)
• Segmenting Italian Sentences for Easy Reading (Marta Cozzini and Horacio Saggion)
• Evaluating Linguistic Speaker Profiles on Response Selection in Multi-Party Dialogue (Maryam Sajedinia, Seyed Mahed Mousavi and Valerio Basile)
• Arbuli Sunnu: A Sicilian-Italian Parallel Treebank (Caterina Maria Cappello, Sabrina D’Alì, Mario Guglielmetti, Elisa Di Nuovo and Cristina Bosco)
• Ellipsis in Enhanced Dependencies: A Case Study on Latin (Lisa Sophie Albertelli, Lorenzo Augello, Giulia Calvi, Annachiara Clementelli, Federica Iurescia and Claudia Corbetta)

16:30 – 17:30 Interview (Paola Merlo, University of Geneva/Idiap Research Institute)

17:30 – 18:30 Oral Presentations

• When Less Is More? Diagnosing ASR Predictions in Sardinian via Layer-Wise Decoding (Domenico De Cristofaro, Alessandro Vietti, Aleese Block and Marianne Pouplier)
• Exploring the Adaptability of Large Speech Models to Non-Verbal Vocalization Task (Juan José Márquez Villacís, Federico D’Asaro, Giuseppe Rizzo and Andrea Bottino)
• FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian (Sara Papi, Marco Gaido, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih Ali Mohamed Nawar and Matteo Negri)
• MAIA: A Benchmark for Multimodal AI Assessment (Davide Testa, Giovanni Bonetta, Raffaella Bernardi, Alessandro Bondielli, Alessandro Lenci, Alessio Miaschi, Lucia C. Passaro and Bernardo Magnini)
• Extending Italian Large Language Models for Vision-language Tasks (Elio Musacchio, Lucia Siciliani, Pierpaolo Basile, Asia Beatrice Uboldi, Giovanni Germani and Giovanni Semeraro)

19:30 – 21:30 Welcome Drink

September 25

09:00 – 10:00 Oral Presentations 

• Linking CompL-it to the LiITA Knowledge Base (Eleonora Litta, Marco Passarotti, Giovanni Moretti, Paolo Brasolin, Valerio Basile, Cristina Bosco, Andrea Di Fabio, Eliana Di Palma, Emiliano Giovannetti, Simone Marchi, Andrea Bellandi and Flavia Sciolette)
• Contemporary Voices in Ancient Tongue: Integrating Papal Encyclicals into the LiLa KB (Aurora Alagni, Federica Iurescia and Eleonora Litta)
• Ciallabacialla! Modeling and Linking a Regional Lexical Resource to Include Sicilian in the Semantic Web (Rachele Sprugnoli, Giovanni Moretti, Domenico Giuseppe Muscianisi and Eleonora Litta)
• Beyond Raw Text: Knowledge-Augmented Italian Relation Extraction with Large Language Models (Gianmaria Balducci, Elisabetta Fersini and Messina Enza)
• Leveraging LLMs to Build a Semi-synthetic Dataset for Legal Information Retrieval: A Case Study on the Italian Civil Code and GPT4-O (Mattia Proietti, Lucia C. Passaro and Alessandro Lenci)

10:00 – 11:00 Poster Session + Coffee Break

• Dissonant Ballerinas and Crafty Carrots: A Comparative Multi-modal Analysis of Italian Brain Rot
  (Anca Dinu, Andra-Maria Florescu, Marius Micluța-Câmpeanu, Ștefana Arina Tăbușcă, Claudiu Creangă and Andreiana Mihail)
• Mapping Meaning in Latin with Large Language Models: A Multi-Task Evaluation of Preverbed Motion Verbs and Spatial Relation Detection in LLMs
  (Andrea Farina, Andrea Ballatore and Barbara McGillivray)
• Linking Emotions: Affective and Lexical Resources for Italian in Linked Open Data
  (Eliana Di Palma, Valerio Basile, Agnese Vardanega, Giuliano Gabrieli and Marco Vassallo)
• PharmaER.IT: An Italian Dataset for Entity Recognition in the Pharmaceutical Domain
  (Andrea Zugarini and Leonardo Rigutini)
• IMB: An Italian Medical Benchmark for Question Answering
  (Antonio Romano, Giuseppe Riccio, Mariano Barone, Marco Postiglione and Vincenzo Moscato)
• Knowledge-Grounded Detection of Factual Hallucinations in Large Language Models
  (Cristian Ceccarelli, Alessandro Raganato and Marco Viviani)
• What Is Better for Syntactic Parsing? A Comparison between Supervised and Unsupervised Models on Dante and Cavalcanti (Claudia Corbetta, Anna Erminia Colombi, Giovanni Moretti and Marco Passarotti)
• Multilingual vs. Monolingual Transformer Models in Encoding Linguistic Structure and Lexical Abstraction (Vivi Nastase, Giuseppe Samo, Chunyang Jiang and Paola Merlo)
• A BERT-Based Approach for Part-of-Speech Tagging in the Low-Resource Context of Sardinian (Salvatore Mario Carta, Filippo Concas, Gianni Fenu, Alessandro Giuliani, Marco Manolo Manca, Mirko Marras, Piergiorgio Mura and Simone Pisano)
• When Figures Speak with Irony: Investigating the Role of Rhetorical Figures in Irony Generation with LLMs (Pier Felice Balestrucci, Michael Oliverio, Soda Marem Lo, Luca Anselma, Valerio Basile, Cristina Bosco, Alessandro Mazzei and Viviana Patti)
• Ontology-Guided Domain Entity Recognition in Environmental Texts: Evaluating Syntax-Driven and LLM Approaches Using BabelNet and GEMET (Elisa Chierchiello, Patricia Chiril, Cristina Bosco and Adriana S. Pagano)
• Seeing Cause and Time: A Visually Grounded Evaluation of Multimodal Models (Salvatore Ergoli, Alessandro Bondielli and Alessandro Lenci)
• Automatic GRI–SDG Annotation and LLM-Based Filtering for Sustainability Reports (Seyed Alireza Mousavian Anaraki, Danilo Croce and Roberto Basili)
• LLMs Struggle on Explicit Causality in Italian (Alessandro Bondielli, Martina Miliani, Luca Paglione, Serena Auriemma, Lucia C. Passaro and Alessandro Lenci)
• Gender Violence in Numbers: Prompting Italian LLMs to Characterize Crimes against Women (Giulia Rizzi, Daniel Scalena and Elisabetta Fersini)
• Analyzing Femicide Reactions in YouTube Comments: A Comparative Study of Giulia Cecchettin and Carol Maltesi (Sveva Silvia Pasini, Marco Madeddu, Chiara Ferrando, Chiara Zanchi and Viviana Patti)
• Semantic Priming in GPT: Investigating LLMs through a Cognitive Psychology Lens (Filippo Colombi and Carlo Strapparava)
• BeaverTails-IT: Towards a Safety Benchmark for Evaluating Italian Large Language Models (Giuseppe Magazzù, Alberto Sormani, Giulia Rizzi, Francesca Pulerà, Daniel Scalena, Stefano Cariddi, Edoardo Michielon, Marco Pasqualini, Claudio Stamile and Elisabetta Fersini)
• Narrative Conflicts: A Tri-Modal Computational Analysis of Antagonism in Shakespeare’s Julius Caesar (Aylin Özkan, İrem Ertaş, Mehmet Can Yavuz and Lucia Cascone)
• AI-Driven Resume Analysis and Enhancement Using Semantic Modeling and Large Language Feedback Loops (Achal Jagadeesh, Chinmayi Ravi Shankar, Sahithya Narayanaswamy Patel, Marco Polignano, Marco Levantesi, Giovanni Semeraro and Ernesto William De Luca)

11:00 – 12:00 Invited Talk: Large Language Models: The Challenge of Evaluation (Karen Fort, Université de Lorraine)

12:00 – 13:30 Oral Presentations 

• Language Models and the Magic of Metaphor: A Comparative Evaluation with Human Judgments (Simone Mazzoli, Alice Suozzi and Gianluca Lebani)
• MAMITA: Benchmarking Misogyny in Italian Memes (Elisabetta Fersini, Francesca Gasparini, Giulia Rizzi and Aurora Saibene)
• Subjectivity in Stereotypes against Migrants in Italian: An Experimental Annotation Procedure (Soda Marem Lo, Marco Antonio Stranisci, Alessandra Teresa Cignarella, Simona Frenda, Valerio Basile, Cristina Bosco, Elisabetta Jezek and Viviana Patti)
• Unveiling Stereotypes: Combining Knowledge Graphs and LLMs for Implied Stereotype Generation (Marco Cuccarini, Lia Draetta, Beatrice Fiumanò, Stefano Bistarelli, Rossana Damiano and Valentina Presutti)
• Linguistic Markers of Population Replacement Conspiracy Theories in YouTube Immigration Discourse (Erik Bran Marino, Davide Bassi and Renata Vieira)
• On the Impact of Hate Speech Synthetic Data on Model Fairness (Camilla Casula and Sara Tonelli)
• MuLTa-Telegram: A Fine-Grained Italian and Polish Dataset for Hate Speech and Target Detection (Elisa Leonardelli, Camilla Casula, Sebastiano Vecellio Salto, Joanna Ewa Bąk, Elisa Muratore, Anna Kołos, Thomas Louf and Sara Tonelli)

13:30 – 14:30 Lunch Break

14:30 – 15:30 Oral Presentations 

• Annotating Manzoni: Challenges in the Annotation of Lemmas, POS and Features in “I Promessi Sposi” (Rachele Sprugnoli and Arianna Redaelli)
• Low- vs High-level Lemmatization for Historical Languages. a Case Study on Italian (Chiara Alzetta and Simonetta Montemagni)
• Veras Audire Et Reddere Voces: A Corpus of Prosodically-Correct Latin Poetic Audio from Large-Language-Model TTS (Michele Ciletti)
• WorthIt: Check-worthiness Estimation of Italian Social Media Posts (Agnese Daffara, Alan Ramponi and Sara Tonelli)
• Gender-Neutral Rewriting in Italian: Models, Approaches, and Trade-offs (Andrea Piergentili, Beatrice Savoldi, Matteo Negri and Luisa Bentivogli)

15:30 – 16:15 Research Communications (Poster Session) + Coffee Break

• Pater Incertus? There Is a Solution: Automatic Discrimination between Cognates and Borrowings for Romance Languages (Liviu P. Dinu, Ana Sabina Uban, Alina Maria Cristea, Simona Georgescu and Laurentiu Zoicas)
• Verba Volant, Scripta Volant? Don’t Worry! There Are Computational Solutions for Protoword Reconstruction (Liviu P. Dinu, Ana Sabina Uban, Alina Maria Cristea, Ioan-Bogdan Iordache, Teodor-George Marchitan, Simona Georgescu and Laurentiu Zoicas)
• Do LLMs Dream of Ontologies? (Marco Bombieri, Simone Paolo Ponzetto and Marco Rospocher)
• Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals
  (Francesco Ortu, Zhijing Jin, Diego Doimo, Mrinmaya Sachan, Alberto Cazzaniga and Bernhard Schölkopf)
• Fine-grained Fallacy Detection with Human Label Variation (Alan Ramponi, Agnese Daffara and Sara Tonelli)
• How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in Italian
  (Andrea Pedrotti, Giulia Rambelli, Caterina Villani and Marianna Bolognesi)
• The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models
  (Diego D.D Doimo, Alessandro Pietro Serra, Alberto Cazzaniga and Alessio A.A. Ansuini)
• What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study (Beatrice Savoldi, Sara Papi, Matteo Negri, Ana Guerberof-Arenas and Luisa Bentivogli)
• Sense-specific Historical Word Usage Generation (Pierluigi Cassotti and Nina Tahmasebi)
• ModaFact: Multi-paradigm Evaluation for Joint Event Modality and Factuality Detection
  (Marco Rovera, Serena Cristoforetti and Sara Tonelli)
• ITALIC: An Italian Culture-Aware Natural Language Benchmark (Andrea Seveso, Daniele Potertì, Edoardo Federici, Mario Mezzanzanica and Fabio Mercorio)
• Language Is Scary When over- Analyzed: Unpacking Implied Misogynistic Reasoning with Argumentation Theory- Driven Prompts (Arianna Muti)
• Delving into Qualitative Implications of Synthetic Data for Hate Speech Detection
  (Camilla Casula, Sebastiano Vecellio Salto, Alan Ramponi and Sara Tonelli)

16:15 – 17:30 Oral Presentations

• Direct and Indirect Interpretations of Speech Acts: Evidence from Human Judgments and Large Language Models (Massimiliano Orsini and Dominique Brunato)
• Crossword Space: Latent Manifold Learning for Italian Crosswords and beyond (Cristiano Ciaccio, Gabriele Sarti, Alessio Miaschi and Felice Dell’Orletta)
• Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models (Agnese Lombardi and Alessandro Lenci)
• The Role of Eye-Tracking Data in Encoder-Based Models: An In-depth Linguistic Analysis (Lucia Domenichelli, Luca Dini, Dominique Brunato and Felice Dell’Orletta)
• Structural Sensitivity Does Not Entail Grammaticality: Assessing LLMs against the Universal Functional Hierarchy (Tommaso Sgrizzi, Asya Zanollo and Cristiano Chesi)
• Positional Bias in Binary Question Answering: How Uncertainty Shapes Model Preferences (Tiziano Labruna, Simone Gallo and Giovanni Da San Martino)

17:30 – 19:00 AILC Meeting

20:00 – 23:00 Social Dinner

September 26

09:00 – 10:30 Oral Presentations 

• Generating and Evaluating Multi-Level Text Simplification: A Case Study on Italian (Michele Papucci, Giulia Venturi and Felice Dell’Orletta)
• PeRAG: Multi-Modal Perspective-Oriented Verbalization with RAG for Inclusive Decision Making (Muhammad Saad Amin, Horacio Jesús Jarquín-Vásquez, Simona Lo Giudice, Franco Sansonetti, Valerio Basile and Viviana Patti)
• What We Learned from Continually Training Minerva: A Case Study on Italian (Luca Moroni, Tommaso Bonomo, Luca Gioffré, Lu Xu, Domenico Fedele, Leonardo Colosi, Andrei Stefan Bejgu, Alessandro Scirè and Roberto Navigli)
• BES4RAG: A Framework for Embedding Model Selection in Retrieval-Augmented Generation (Lorenzo Canale, Stefano Scotta, Alberto Messina and Laura Farinetti)
• The OuLiBench Benchmark: Formal Constraints as a Lens into LLM Linguistic Competence (Silvio Calderaro, Alessio Miaschi and Felice Dell’Orletta)
• A Modular LLM-based Dialog System for Accessible Exploration of Finite State Automata (Stefano Vittorio Porta, Pier Felice Balestrucci, Michael Oliverio, Luca Anselma and Alessandro Mazzei)
• Evaluating Italian and English Small Language Models for Domain-based QA in Low-Resource Scenario (Irene Siragusa and Roberto Pirrone)

10:30 – 11:30 Poster Session + Coffee Break

• Detecting Semantic Intertextuality in Ancient Greek Literature: A Computational Approach.
  Caterina D’Angelo, Andrea Taddei and Alessandro Lenci
• Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark
  (Enrico Mensa, Lorenzo Zane, Calogero Jerik Scozzaro, Matteo Delsanto, Tommaso Milani and Daniele P. Radicioni)
• Uni-Mate: A Retrieval-Augmented Generation System to Provide High School Students with Accurate Academic Guidance (Samuele Mazzei, Lorenzo Zambotto, Gabriele Tealdo, Alberto Macagno and Alessio Palmero Aprosio)
• Context-Aware Search Space Adaptation of Hyperparameters and Architectures for AutoML in Text Classification (Parisa Safikhani and David Broneske)
• BLiMP-IT: Harnessing Automatic Minimal Pair Generation for Italian Language Model Evaluation
  (Matilde Barbini, Maria Letizia Piccini Bianchessi, Veronica Bressan, Achille Fusco, Sarah Rossi, Sofia Neri, Tommaso Sgrizzi and Cristiano Chesi)
• Strategic Conversations: LLMs Argumentation and User Perception in Movie Recommendation Dialogues
  (Valeria Mauro, Martina Di Bratto, Valentina Russo, Azzurra Mancini and Marco Grazioso)
• Probing Feminist Representations: A Study of Bias in LLMs and Word Embeddings
  (Arianna Muti, Elisa Bassignana, Emanuele Moscato and Debora Nozza)
• A Multilingual Investigation of Anthropocentrism in GPT-4O
  (Francesca Grasso and Stefano Locci)
• Toward Optimised Datasets to Fine-tune ASR Systems Leveraging Less but More Informative Speech.
  (Loredana Schettino, Vincenzo Norman Vitale and Alessandro Vietti)
• Surprisal and Crossword Clues Difficulty: Evaluating Linguistic Processing between LLMs and Humans
  (Tommaso Iaquinta, Kamyar Zeinalipour, Achille Fusco, Asya Zanollo and Cristiano Chesi)
• “I Understand, but…”: Towards a Comprehensive Account of the Explainee’s Voice in Explanatory Dialogues (Andrea Zaninello, Petar Bodlovic, Marcin Lewinski and Bernardo Magnini)
• Acquisition in Babies and Machines: Comparing the Learning Trajectories of LMs in Terms of Syntactic Structures (ATTracTSS Test Set)
  (Sarah Rossi, Guido Formichi, Sofia Neri, Tommaso Sgrizzi, Asya Zanollo, Veronica Bressan and Cristiano Chesi)
• The Meaning of Beatus: Disambiguating Latin with Contemporary AI Models
  (Eleonora Ghizzota, Pierpaolo Basile, Lucia Siciliani and Giovanni Semeraro)
• Diffusion-Aided RAG: Elevating Dense-Retrieval Chatbots via Graph-Based Diffusion Reranking
  (Sai Teja Dampanaboina, Sai Nishchal Gamini, Karishma Kunwar, Marco Polignano, Marco Levantesi, Giovanni Semeraro and Ernesto William De Luca)
• Bidirectional Emotional Influence in Human–LLM Interaction: Empirical Analysis and Methodological Framework
  (Manuel Gozzi and Francesca Fallucchi)
• Towards the Semi-Automated Population of the Ancient Greek WordNet
  (Beatrice Marchesi, Annachiara Clementelli, Andrea Maurizio Mammarella, Silvia Zampetta, Erica Biagetti, Luca Brigada Villa, Virginia Mastellari, Riccardo Ginevra, Claudia Roberta Combei and Chiara Zanchi)
• Verso La Valutazione Automatizzata Dell’italiano L2: ETET Tra LLM E Tecnologie Vocali
  (Claudia Roberta Combei, Anna Vignoli and Francesco Zappulla)
• A Hypothesis-Driven Framework for Detecting Lexical Semantic Change
  (Pierluigi Cassotti and Nina Tahmasebi)
• LEARN: On the Feasibility of Learner Error AutoRegressive Neural Annotation
  (Paolo Gajo, Daniele Polizzi, Adriano Ferraresi and Alberto Barrón-Cedeño)
• MLLMs Construction Company: Investigating Multimodal LLMs’ Communicative Skills in a Collaborative Building Task (Marika Sarzotti, Giovanni Duca, Chris Madge, Raffaella Bernardi and Massimo Poesio)

11:30 – 12:30 Invited Talk: A Blueprint for Foundation Models with Adaptive Tokenization and Memory (Edoardo Maria Ponti, University of Edimburgh/NVIDIA)

12:30 – 13:30 Oral Presentations

• Meta-evaluation of Automatic Machine Translation Metrics between Italian and a Minor Language Variety of German (Paolo Di Natale, Elena Chiocchetti and Egon Waldemar Stemle)
• DIETA: A Decoder-only Transformer-based Model for Italian-English Machine TrAnslation (Pranav Kasela, Marco Braga, Alessandro Ghiotto, Andrea Pilzer, Marco Viviani and Alessandro Raganato)
• Balancing Translation Quality and Environmental Impact: Comparing Large and Small Language Models (Antonio Castaldo, Petra Giommarelli and Johanna Monti)
• A Tough Hoe to Row: Instruction Fine-Tuning LLaMA 3.2 for Multilingual Idiom Processing (Debora Ciminari and Alberto Barrón-Cedeño)
• Evaluating Large Language Models on Wikipedia Graph Navigation: Insights from the WikiGame (Daniele Margiotta, Danilo Croce and Roberto Basili)

13:30 – 14:30 Lunch Break

14:30 – 15:30 Oral Presentations

• MedBench-IT: A Comprehensive Benchmark for Evaluating Large Language Models on Italian Medical Entrance Examinations (Ruggero Marino Lazzaroni, Alessandro Angioi, Michelangelo Puliga, Davide Sanna and Roberto Marras)
• Doctor, Is That You? Evaluating Large Language Models on Italy’s Medical School Entrance Exams (Ruben Piperno, Agnese Bonfigli, Felice Dell’Orletta, Leandro Pecchia, Mario Merone and Luca Bacco)
• Mamma Mia! Where’s My Name? De-Identifying Italian Clinical Notes with Large Language Models (Michele Miranda, Sébastien Bratières, Stefano Patarnello and Livia Lilli)
• A Novel Real-World Dataset of Italian Clinical Notes for NLP-based Decision Support in Low Back Pain Treatment (Agnese Bonfigli, Ruben Piperno, Luca Bacco, Felice Dell’Orletta, Dominique Brunato, Filippo Crispino, Giuseppe Francesco Papalia, Fabrizio Russo, Gianluca Vadalà, Rocco Papalia, Mario Merone and Leandro Pecchia)
• Using End-to-End Automatic Speech Recognizers’ Internals to Model Disfluencies in Italian Patients with Early-stage Parkinson’s Disease (Loredana Schettino, Vincenzo Norman Vitale and Marta Maffia)

15:30 – 16:00 Coffee Break

16:00 – 17:00 Oral Presentations

• Can LLMs Help Recollect and Elaborate on Our Personal Experiences? (Gabriel Roccabruna, Olha Khomyn, Michele Yin and Giuseppe Riccardi)
• Protecting the Privacy in Velvet with Model Editing (Giancarlo A. Xompero, Elena Sofia Ruzzetti, Cristina Giannone, Andrea Favalli, Raniero Romagnoli and Fabio Massimo Zanzotto)
• Uncovering Unsafety Traits in Italian Language Models (Giulia Rizzi, Giuseppe Magazzù, Alberto Sormani, Francesca Pulerà, Daniel Scalena and Elisabetta Fersini)
• Benchmarking Large Language Models for Target-Based Financial Sentiment Analysis (Iftikhar Muhammad, Marco Rospocher, Timotej Knez and Slavko Žitnik)
• Sparse Autoencoders Find Partially Interpretable Features in Italian Small Language Models (Alessandro Bondielli, Lucia C. Passaro and Alessandro Lenci)

17:00 - 17:15 Closing Session