Leonardo Ranaldi

74 papers A* 4Misc 3Journal 29Unranked 38

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models. CoRR Gabriele Maraia, Marco Valentino, Fabio Massimo Zanzotto, Leonardo Ranaldi
2026	—	`conf`	Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language Models. EACL (Volume 1: Long Papers) Gabriele Maraia, Leonardo Ranaldi, Marco Valentino, Fabio Massimo Zanzotto
2026	—	`conf`	Learning Multilingual Agentic Policy to Control Sycophancy. EACL (Volume 1: Long Papers) Leonardo Ranaldi, Giulia Pucci
2026	—	`conf`	Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Question Answering Task. EACL (Findings) Leonardo Ranaldi
2025	A*	`conf`	Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent. EMNLP Giulia Pucci, Leonardo Ranaldi
2025	J	`jnl`	Animate, or Inanimate, That Is the Question for Large Language Models. Inf. Giulia Pucci, Fabio Massimo Zanzotto, Leonardo Ranaldi
2025	J	`jnl`	Challenging the Abilities of Large Language Models in Italian: a Community Initiative. CoRR Malvina Nissim, Danilo Croce, Viviana Patti, Pierpaolo Basile, Giuseppe Attanasio, Elio Musacchio, Matteo Rinaldi, Federico Borazio, Maria Francis, Jacopo Gili, Daniel Scalena, Begoña Altuna, Ekhi Azurmendi, Valerio Basile, Luisa Bentivogli, Arianna Bisazza, Marianna Bolognesi, Dominique Brunato, Tommaso Caselli, Silvia Casola, Maria Cassese, Mauro Cettolo, Claudia Collacciani, Leonardo De Cosmo, Maria Pia di Buono, Andrea Esuli, Julen Etxaniz, Chiara Ferrando, Alessia Fidelangeli, Simona Frenda, Achille Fusco, Marco Gaido, Andrea Galassi, Federico Galli, Luca Giordano, Mattia Goffetti, Itziar Gonzalez-Dios, Lorenzo Gregori, Giulia Grundler, Sandro Iannaccone, Chunyang Jiang, Moreno La Quatra, Francesca Lagioia, Soda Marem Lo, Marco Madeddu, Bernardo Magnini, Raffaele Manna, Fabio Mercorio, Paola Merlo, Arianna Muti, Vivi Nastase, Matteo Negri, Dario Onorati, Elena Palmieri, Sara Papi, Lucia C. Passaro, Giulia Pensa, Andrea Piergentili, Daniele Potertì, Giovanni Puccetti, Federico Ranaldi, Leonardo Ranaldi, Andrea Amelio Ravelli, Martina Rosola, Elena Sofia Ruzzetti, Giuseppe Samo, Andrea Santilli, Piera Santin, Gabriele Sarti, Giovanni Sartor, Beatrice Savoldi, Antonio Serino, Andrea Seveso, Lucia Siciliani, Paolo Torroni, Rossella Varvara, Andrea Zaninello, Asya Zanollo, Fabio Massimo Zanzotto, Kamyar Zeinalipour, Andrea Zugarini
2025	J	`jnl`	Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation Strategies. CoRR Maël Jullien, Marco Valentino, Leonardo Ranaldi, André Freitas
2025	—	`conf`	Eliciting Critical Reasoning in Retrieval-Augmented Generation via Contrastive Explanations. NAACL (Long Papers) Leonardo Ranaldi, Marco Valentino, André Freitas
2025	—	`conf`	Exploring Backward Reasoning in Large Language Models. NAACL (Findings) Leonardo Ranaldi, Giulia Pucci
2025	—	`conf`	Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions. ACL (1) Leonardo Ranaldi, Marco Valentino, André Freitas
2025	J	`jnl`	Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions. CoRR Leonardo Ranaldi, Marco Valentino, Alexander Polonsky, André Freitas
2025	A*	`conf`	Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations. EMNLP Leonardo Ranaldi, Federico Ranaldi, Fabio Massimo Zanzotto, Barry Haddow, Alexandra Birch
2025	J	`jnl`	Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations. CoRR Leonardo Ranaldi, Federico Ranaldi, Fabio Massimo Zanzotto, Barry Haddow, Alexandra Birch
2025	J	`jnl`	MeMo: Towards Language Models with Associative Memory Mechanisms. CoRR Fabio Massimo Zanzotto, Elena Sofia Ruzzetti, Giancarlo A. Xompero, Leonardo Ranaldi, Davide Venditti, Federico Ranaldi, Cristina Giannone, Andrea Favalli, Raniero Romagnoli
2025	—	`conf`	Multilingual Reasoning via Self-training. NAACL (Long Papers) Leonardo Ranaldi, Giulia Pucci
2025	J	`jnl`	Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task. CoRR Leonardo Ranaldi, Barry Haddow, Alexandra Birch
2025	—	`conf`	No Longer Left Behind: Self-training Reasoning Models in Italian. CLiC-it Federico Ranaldi, Leonardo Ranaldi
2025	—	`conf`	Position Paper: MeMo: Towards Language Models with Associative Memory Mechanisms. ACL (Findings) Fabio Massimo Zanzotto, Elena Sofia Ruzzetti, Giancarlo A. Xompero, Leonardo Ranaldi, Davide Venditti, Federico Ranaldi, Cristina Giannone, Andrea Favalli, Raniero Romagnoli
2025	J	`jnl`	Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs. CoRR Federico Ranaldi, Andrea Zugarini, Leonardo Ranaldi, Fabio Massimo Zanzotto
2025	—	`conf`	R2-MultiOmnia: Leading Multilingual Multimodal Reasoning via Self-Training. ACL (1) Leonardo Ranaldi, Federico Ranaldi, Giulia Pucci
2025	J	`jnl`	Survey on the Role of Mechanistic Interpretability in Generative AI. Big Data Cogn. Comput. Leonardo Ranaldi
2025	J	`jnl`	Transferring Reasoning Capabilities between LLMs operating via Curriculum Learning Policy. Trans. Mach. Learn. Res. Leonardo Ranaldi, Giulia Pucci, Fabio Massimo Zanzotto
2025	—	`conf`	When natural language is not enough: The limits of in-context learning demonstrations in multilingual reasoning. NAACL (Findings) Leonardo Ranaldi, Barry Haddow, Alexandra Birch
2024	—	`conf`	A Tree-of-Thoughts to Broaden Multi-step Reasoning across Languages. NAACL-HLT (Findings) Leonardo Ranaldi, Giulia Pucci, Federico Ranaldi, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto
2024	—	`conf`	A Trip Towards Fairness: Bias and De-Biasing in Large Language Models. *SEM@NAACL Leonardo Ranaldi, Elena Sofia Ruzzetti, Davide Venditti, Dario Onorati, Fabio Massimo Zanzotto
2024	—	`conf`	Aligning Large and Small Language Models via Chain-of-Thought Reasoning. EACL (1) Leonardo Ranaldi, André Freitas
2024	J	`jnl`	Animate, or Inanimate, That is the Question for Large Language Models. CoRR Leonardo Ranaldi, Giulia Pucci, Fabio Massimo Zanzotto
2024	—	`conf`	Assessing the Asymmetric Behaviour of Italian Large Language Models across Different Syntactic Structures. CLiC-it Elena Sofia Ruzzetti, Federico Ranaldi, Dario Onorati, Davide Venditti, Leonardo Ranaldi, Tommaso Caselli, Fabio Massimo Zanzotto
2024	—	`conf`	Does the Language Matter? Curriculum Learning over Neo-Latin Languages. LREC/COLING Giulia Pucci, Leonardo Ranaldi
2024	J	`jnl`	Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations. CoRR Leonardo Ranaldi, Marco Valentino, André Freitas
2024	A*	`conf`	Empowering Multi-step Reasoning across Languages via Program-Aided Language Models. EMNLP Leonardo Ranaldi, Giulia Pucci, Barry Haddow, Alexandra Birch
2024	—	`conf`	Empowering cross-lingual abilities of instruction-tuned large language models by translation-following demonstrations. ACL (Findings) Leonardo Ranaldi, Giulia Pucci, André Freitas
2024	—	`conf`	HANS, are you clever? Clever Hans Effect Analysis of Neural Systems. *SEM@NAACL Leonardo Ranaldi, Fabio Massimo Zanzotto
2024	—	`conf`	How Far Does the Sequence of Compositions Impact Multilingual Pre-Training? CLiC-it Leonardo Ranaldi, Giulia Pucci, Fabio Massimo Zanzotto
2024	J	`jnl`	Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation. CoRR Federico Ranaldi, Elena Sofia Ruzzetti, Dario Onorati, Leonardo Ranaldi, Cristina Giannone, Andrea Favalli, Raniero Romagnoli, Fabio Massimo Zanzotto
2024	—	`conf`	Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL translation. ACL (Findings) Federico Ranaldi, Elena Sofia Ruzzetti, Dario Onorati, Leonardo Ranaldi, Cristina Giannone, Andrea Favalli, Raniero Romagnoli, Fabio Massimo Zanzotto
2024	—	`conf`	Measuring Bias in Instruction-Following Models with ItaP-AT for the Italian Language. CLiC-it Dario Onorati, Davide Venditti, Elena Sofia Ruzzetti, Federico Ranaldi, Leonardo Ranaldi, Fabio Massimo Zanzotto
2024	A*	`conf`	Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models. EMNLP Leonardo Ranaldi, André Freitas
2024	J	`jnl`	Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models. CoRR Leonardo Ranaldi, André Freitas
2024	—	`conf`	Termite Italian Text-to-SQL: A CALAMITA Challenge. CLiC-it Federico Ranaldi, Elena Sofia Ruzzetti, Dario Onorati, Fabio Massimo Zanzotto, Leonardo Ranaldi
2024	—	`conf`	The limits of Italian in Reasoning Tasks. CLiC-it Leonardo Ranaldi, Giulia Pucci, Federico Ranaldi, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto
2023	J	`jnl`	A Trip Towards Fairness: Bias and De-Biasing in Large Language Models. CoRR Leonardo Ranaldi, Elena Sofia Ruzzetti, Davide Venditti, Dario Onorati, Fabio Massimo Zanzotto
2023	—	`conf`	Are All Languages Equal? Curriculum Learning over Different Languages. CLiC-it Giulia Pucci, Leonardo Ranaldi, Fabio Massimo Zanzotto
2023	J	`jnl`	Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrations. CoRR Leonardo Ranaldi, Giulia Pucci, André Freitas
2023	J	`jnl`	Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts. CoRR Leonardo Ranaldi, Fabio Massimo Zanzotto
2023	—	`conf`	Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages. EMNLP (Findings) Elena Sofia Ruzzetti, Federico Ranaldi, Felicia Logozzo, Michele Mastromattei, Leonardo Ranaldi, Fabio Massimo Zanzotto
2023	J	`jnl`	Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages. CoRR Federico Ranaldi, Elena Sofia Ruzzetti, Felicia Logozzo, Michele Mastromattei, Leonardo Ranaldi, Fabio Massimo Zanzotto
2023	—	`conf`	Investigating Gender Bias in Large Language Models for the Italian Language. CLiC-it Elena Sofia Ruzzetti, Dario Onorati, Leonardo Ranaldi, Davide Venditti, Fabio Massimo Zanzotto
2023	—	`conf`	Legal Summarization: to Each Court its Own Model. CLiC-it Flavia Achena, David Preti, Davide Venditti, Leonardo Ranaldi, Cristina Giannone, Fabio Massimo Zanzotto, Andrea Favalli, Raniero Romagnoli
2023	—	`conf`	Measuring bias in Instruction-Following models with P-AT. EMNLP (Findings) Dario Onorati, Elena Sofia Ruzzetti, Davide Venditti, Leonardo Ranaldi, Fabio Massimo Zanzotto
2023	Misc	`conf`	Modeling Easiness for Training Transformers with Curriculum Learning. RANLP Leonardo Ranaldi, Giulia Pucci, Fabio Massimo Zanzotto
2023	Misc	`conf`	PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models. RANLP Leonardo Ranaldi, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto
2023	J	`jnl`	PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models. CoRR Leonardo Ranaldi, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto
2023	—	`conf`	Prompting LLMs in Italian Language for Text-to-SQL Translation. CLiC-it Federico Ranaldi, Elena Sofia Ruzzetti, Leonardo Ranaldi, Davide Venditti, Cristina Giannone, Andrea Favalli, Raniero Romagnoli, Fabio Massimo Zanzotto
2023	—	`conf`	Teasing LLMs Adapted to Italian. CLiC-it Leonardo Ranaldi, Giulia Pucci, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto, André Freitas
2023	Misc	`conf`	The Dark Side of the Language: Pre-trained Transformers in the DarkNet. RANLP Leonardo Ranaldi, Aria Nourbakhsh, Elena Sofia Ruzzetti, Arianna Patrizi, Dario Onorati, Michele Mastromattei, Francesca Fallucchi, Fabio Massimo Zanzotto
2023	—	`conf`	The Dark Side of the Language: Syntax-Based Neural Networks Rivaling Transformers in Definitely Unseen Sentences. WI/IAT Dario Onorati, Leonardo Ranaldi, Aria Nourbakhsh, Arianna Patrizi, Elena Sofia Ruzzetti, Michele Mastromattei, Francesca Fallucchi, Fabio Massimo Zanzotto
2023	J	`jnl`	When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour. CoRR Leonardo Ranaldi, Giulia Pucci
2022	—	`conf`	C-OSINT: COVID-19 Open Source Artificial INTelligence Framework. ITASEC Leonardo Ranaldi, Aria Nourbakhsh, Francesca Fallucchid, Fabio Massimo Zanzotto
2022	J	`jnl`	CryptoNet: Using Auto-Regressive Multi-Layer Artificial Neural Networks to Predict Financial Time Series. Inf. Leonardo Ranaldi, Marco Gerardi, Francesca Fallucchi
2022	J	`jnl`	Dis-Cover AI Minds to Preserve Human Knowledge. Future Internet Leonardo Ranaldi, Francesca Fallucchi, Fabio Massimo Zanzotto
2022	—	`conf`	Lacking the Embedding of a Word? Look it up into a Traditional Dictionary. ACL (Findings) Elena Sofia Ruzzetti, Leonardo Ranaldi, Michele Mastromattei, Francesca Fallucchi, Noemi Scarpato, Fabio Massimo Zanzotto
2022	—	`conf`	Machine Learning Techniques for Italian Phishing Detection. ITASEC Leonardo Ranaldi, Michele Petito, Marco Gerardi, Francesca Fallucchid, Fabio Massimo Zanzotto
2022	J	`jnl`	Shedding Light on the Dark Web: Authorship Attribution in Radical Forums. Inf. Leonardo Ranaldi, Federico Ranaldi, Francesca Fallucchi, Fabio Massimo Zanzotto
2022	J	`jnl`	Syntax and prejudice: ethically-charged biases of a syntax-based hate speech recognizer unveiled. PeerJ Comput. Sci. Michele Mastromattei, Leonardo Ranaldi, Francesca Fallucchi, Fabio Massimo Zanzotto
2022	J	`jnl`	The Dark Side of the Language: Pre-trained Transformers in the DarkNet. CoRR Leonardo Ranaldi, Aria Nourbakhsh, Arianna Patrizi, Elena Sofia Ruzzetti, Dario Onorati, Francesca Fallucchi, Fabio Massimo Zanzotto
2021	—	`conf`	KERMIT for Sentiment Analysis in Italian Healthcare Reviews. CLiC-it Leonardo Ranaldi, Michele Mastromattei, Dario Onorati, Elena Sofia Ruzzetti, Francesca Fallucchi, Fabio Massimo Zanzotto
2021	—	`conf`	KERMITviz: Visualizing Neural Network Activations on Syntactic Trees. MTSR Leonardo Ranaldi, Francesca Fallucchi, Andrea Santilli, Fabio Massimo Zanzotto
2021	J	`jnl`	Lacking the embedding of a word? Look it up into a traditional dictionary. CoRR Elena Sofia Ruzzetti, Leonardo Ranaldi, Michele Mastromattei, Francesca Fallucchi, Fabio Massimo Zanzotto
2020	J	`jnl`	Hiding Your Face Is Not Enough: user identity linkage with image recognition. Soc. Netw. Anal. Min. Leonardo Ranaldi, Fabio Massimo Zanzotto
2020	—	`conf`	KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations. EMNLP (1) Fabio Massimo Zanzotto, Andrea Santilli, Leonardo Ranaldi, Dario Onorati, Pierfrancesco Tommasino, Francesca Fallucchi
2020	J	`jnl`	Pat-in-the-Loop: Declarative Knowledge for Controlling Neural Networks. Future Internet Dario Onorati, Pierfrancesco Tommasino, Leonardo Ranaldi, Francesca Fallucchi, Fabio Massimo Zanzotto
2020	—	`conf`	Pat-in-the-loop: Syntax-based Neural Networks with Activation Visualization and Declarative Control. XAI.it@AI*IA Fabio Massimo Zanzotto, Dario Onorati, Pierfrancesco Tommasino, Andrea Santilli, Leonardo Ranaldi, Francesca Fallucchi