Gabriele Sarti

53 papers A* 4C 1Journal 30Unranked 18

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents. CoRR Raghu Arghal, Fade Chen, Niall Dalton, Evgenii Kortukov, Calum McNamara, Angelos Nalmpantis, Moksh Nirvaan, Gabriele Sarti, Mario Giulianelli
2026	J	`jnl`	Agents of Chaos. CoRR Natalie Shapira, Chris Wendler, Avery Yen, Gabriele Sarti, Koyena Pal, Olivia Floody, Adam Belfki, Alexander R. Loftus, Aditya Ratan Jannali, Nikhil Prakash, Jasmine Cui, Giordano Rogers, Jannik Brinkmann, Can Rager, Amir Zur, Michael Ripa, Aruna Sankaranarayanan, David Atkinson, Rohit Gandikota, Jaden Fiotto-Kaufman, Eunjeong Hwang, Hadas Orgad, P. Sam Sahil, Negev Taglicht, Tomer Shabtay, Atai Ambus, Nitay Alon, Shiri Oron, Ayelet Gordon-Tapiero, Yotam Kaplan, Vered Shwartz, Tamar Rott Shaham, Christoph Riedl, Reuth Mirsky, Maarten Sap, David Manheim, Tomer Ullman, David Bau
2026	—	`conf`	Cruciverb-IT at EVALITA 2026: Overview of the Crossword Solving in Italian Task. EVALITA Cristiano Ciaccio, Gabriele Sarti, Alessio Miaschi, Felice Dell'Orletta, Malvina Nissim
2026	J	`jnl`	Distilling Formal Logic into Neural Spaces: A Kernel Alignment Approach for Signal Temporal Logic. CoRR Sara Candussio, Gabriele Sarti, Gaia Saveri, Luca Bortolussi
2026	—	`conf`	Steering Large Language Models for Machine Translation Personalization. EACL (Volume 1: Long Papers) Daniel Scalena, Gabriele Sarti, Arianna Bisazza, Elisabetta Fersini, Malvina Nissim
2026	—	`conf`	TIGRO at FadeIT: E Pluribus Unum - A Multi-task Approach to Fallacy Detection and Span Identification. EVALITA Stefano Atzeni, Gabriele Sarti, Tommaso Caselli, Malvina Nissim
2025	—	`conf`	Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers. ECML/PKDD (5) Sara Candussio, Gaia Saveri, Gabriele Sarti, Luca Bortolussi
2025	J	`jnl`	Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers. CoRR Sara Candussio, Gaia Saveri, Gabriele Sarti, Luca Bortolussi
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	—	`conf`	Crossword Space: Latent Manifold Learning for Italian Crosswords and beyond. CLiC-it Cristiano Ciaccio, Gabriele Sarti, Alessio Miaschi, Felice Dell'Orletta
2025	J	`jnl`	Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models. CoRR Dana Arad, Yonatan Belinkov, Hanjie Chen, Najoung Kim, Hosein Mohebbi, Aaron Mueller, Gabriele Sarti, Martin Tutek
2025	J	`jnl`	Interpreto: An Explainability Library for Transformers. CoRR Antonin Poché, Thomas Mullor, Gabriele Sarti, Frédéric Boisnard, Corentin Friedrich, Charlotte Claye, François Hoofd, Raphael Bernas, Céline Hudelot, Fanny Jourdan
2025	J	`jnl`	Noiser: Bounded Input Perturbations for Attributing Large Language Models. CoRR Mohammad Reza Ghasemi Madani, Aryo Pradipta Gema, Gabriele Sarti, Yu Zhao, Pasquale Minervini, Andrea Passerini
2025	J	`jnl`	QE4PE: Word-level Quality Estimation for Human Post-Editing. CoRR Gabriele Sarti, Vilém Zouhar, Grzegorz Chrupala, Ana Guerberof Arenas, Malvina Nissim, Arianna Bisazza
2025	J	`jnl`	QE4PE: Word-level Quality Estimation for Human Post-Editing. Trans. Assoc. Comput. Linguistics Gabriele Sarti, Vilém Zouhar, Grzegorz Chrupala, Ana Guerberof Arenas, Malvina Nissim, Arianna Bisazza
2025	J	`jnl`	Reveal-Bangla: A Dataset for Cross-Lingual Multi-Step Reasoning Evaluation. CoRR Khondoker Ittehadul Islam, Gabriele Sarti
2025	J	`jnl`	Steering Large Language Models for Machine Translation Personalization. CoRR Daniel Scalena, Gabriele Sarti, Arianna Bisazza, Elisabetta Fersini, Malvina Nissim
2025	A*	`conf`	Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement. EMNLP Gabriele Sarti, Vilém Zouhar, Malvina Nissim, Arianna Bisazza
2025	J	`jnl`	Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement. CoRR Gabriele Sarti, Vilém Zouhar, Malvina Nissim, Arianna Bisazza
2024	J	`jnl`	A Primer on the Inner Workings of Transformer-based Language Models. CoRR Javier Ferrando, Gabriele Sarti, Arianna Bisazza, Marta R. Costa-jussà
2024	J	`jnl`	Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation. Trans. Assoc. Comput. Linguistics Lukas Edman, Gabriele Sarti, Antonio Toral, Gertjan van Noord, Arianna Bisazza
2024	—	`conf`	DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers. NAACL-HLT (Findings) Anna Langedijk, Hosein Mohebbi, Gabriele Sarti, Willem H. Zuidema, Jaap Jumelet
2024	—	`conf`	Democratizing Advanced Attribution Analyses of Generative Language Models with the Inseq Toolkit. xAI (Late-breaking Work, Demos, Doctoral Consortium) Gabriele Sarti, Nils Feldhus, Jirui Qi, Malvina Nissim, Arianna Bisazza
2024	—	`conf`	EurekaRebus - Verbalized Rebus Solving with LLMs: A CALAMITA Challenge. CLiC-it Gabriele Sarti, Tommaso Caselli, Arianna Bisazza, Malvina Nissim
2024	—	`conf`	IT5: Text-to-text Pretraining for Italian Language Understanding and Generation. LREC/COLING Gabriele Sarti, Malvina Nissim
2024	A*	`conf`	Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation. EMNLP Jirui Qi, Gabriele Sarti, Raquel Fernández, Arianna Bisazza
2024	J	`jnl`	Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation. CoRR Jirui Qi, Gabriele Sarti, Raquel Fernández, Arianna Bisazza
2024	J	`jnl`	Multi-property Steering of Large Language Models with Dynamic Activation Composition. CoRR Daniel Scalena, Gabriele Sarti, Malvina Nissim
2024	—	`conf`	Non Verbis, Sed Rebus: Large Language Models Are Weak Solvers of Italian Rebuses. CLiC-it Gabriele Sarti, Tommaso Caselli, Malvina Nissim, Arianna Bisazza
2024	J	`jnl`	Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses. CoRR Gabriele Sarti, Tommaso Caselli, Malvina Nissim, Arianna Bisazza
2024	A*	`conf`	Quantifying the Plausibility of Context Reliance in Neural Machine Translation. ICLR Gabriele Sarti, Grzegorz Chrupala, Malvina Nissim, Arianna Bisazza
2023	—	`conf`	Contrastive Language-Image Pre-training for the Italian Language. CLiC-it Federico Bianchi, Giuseppe Attanasio, Raphael Pisoni, Silvia Terragni, Gabriele Sarti, Dario Balestri
2023	J	`jnl`	DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers. CoRR Anna Langedijk, Hosein Mohebbi, Gabriele Sarti, Willem H. Zuidema, Jaap Jumelet
2023	—	`conf`	Inseq: An Interpretability Toolkit for Sequence Generation Models. ACL (demo) Gabriele Sarti, Nils Feldhus, Ludwig Sickert, Oskar van der Wal
2023	J	`jnl`	Inseq: An Interpretability Toolkit for Sequence Generation Models. CoRR Gabriele Sarti, Nils Feldhus, Ludwig Sickert, Oskar van der Wal
2023	J	`jnl`	Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence. CoRR Daniel Scalena, Gabriele Sarti, Malvina Nissim, Elisabetta Fersini
2023	J	`jnl`	Quantifying the Plausibility of Context Reliance in Neural Machine Translation. CoRR Gabriele Sarti, Grzegorz Chrupala, Malvina Nissim, Arianna Bisazza
2023	—	`conf`	RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation. ACL (2) Gabriele Sarti, Phu Mon Htut, Xing Niu, Benjamin Hsu, Anna Currey, Georgiana Dinu, Maria Nadejde
2023	J	`jnl`	RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation. CoRR Gabriele Sarti, Phu Mon Htut, Xing Niu, Benjamin Hsu, Anna Currey, Georgiana Dinu, Maria Nadejde
2022	A*	`conf`	DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages. EMNLP Gabriele Sarti, Arianna Bisazza, Ana Guerberof Arenas, Antonio Toral
2022	J	`jnl`	DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages. CoRR Gabriele Sarti, Arianna Bisazza, Ana Guerberof Arenas, Antonio Toral
2022	J	`jnl`	IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation. CoRR Gabriele Sarti, Malvina Nissim
2022	C	`conf`	InDeep $\times$ NMT: Empowering Human Translators via Interpretable Neural Machine Translation. EAMT Gabriele Sarti, Arianna Bisazza
2021	J	`jnl`	A dissemination workshop for introducing young Italian students to NLP. CoRR Lucio Messina, Lucia Busso, Claudia Roberta Combei, Ludovica Pannitto, Alessio Miaschi, Gabriele Sarti, Malvina Nissim
2021	J	`jnl`	Contrastive Language-Image Pre-training for the Italian Language. CoRR Federico Bianchi, Giuseppe Attanasio, Raphael Pisoni, Silvia Terragni, Gabriele Sarti, Sri Lakshmi
2021	J	`jnl`	Teaching NLP with Bracelets and Restaurant Menus: An Interactive Workshop for Italian Students. CoRR Ludovica Pannitto, Lucia Busso, Claudia Roberta Combei, Lucio Messina, Alessio Miaschi, Gabriele Sarti, Malvina Nissim
2021	—	`conf`	That Looks Hard: Characterizing Linguistic Complexity in Humans and Language Models. CMLS Gabriele Sarti, Dominique Brunato, Felice Dell'Orletta
2020	—	`conf`	ArchiMeDe @ DANKMEMES: A New Model Architecture for Meme Detection. EVALITA Jinen Setpal, Gabriele Sarti
2020	—	`conf`	ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation. NL4AI@AI*IA Ginevra Carbone, Gabriele Sarti
2020	J	`jnl`	ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation. CoRR Ginevra Carbone, Gabriele Sarti
2020	—	`conf`	Italian Transformers Under the Linguistic Lens. CLiC-it Alessio Miaschi, Gabriele Sarti, Dominique Brunato, Felice Dell'Orletta, Giulia Venturi
2020	—	`conf`	UmBERTo-MTSA @ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations (short paper). EVALITA Gabriele Sarti
2020	J	`jnl`	UmBERTo-MTSA @ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations. CoRR Gabriele Sarti