KERMIT: Complementing transformer architectures with encoders of explicit syntactic interpretations FM Zanzotto, A Santilli, L Ranaldi, D Onorati, P Tommasino, F Fallucchi Proceedings of the 2020 conference on empirical methods in natural language …, 2020 | 60 | 2020 |
Knowing knowledge: Epistemological study of knowledge in transformers L Ranaldi, G Pucci Applied Sciences 13 (2), 677, 2023 | 41 | 2023 |
A trip towards fairness: Bias and de-biasing in large language models L Ranaldi, ES Ruzzetti, D Venditti, D Onorati, FM Zanzotto Proceedings of the 13th Joint Conference on Lexical and Computational …, 2023 | 33 | 2023 |
When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour L Ranaldi, G Pucci arXiv preprint arXiv:2311.09410, 2023 | 21 | 2023 |
Dis-cover ai minds to preserve human knowledge L Ranaldi, F Fallucchi, FM Zanzotto Future Internet 14 (1), 10, 2021 | 21 | 2021 |
Aligning large and small language models via chain-of-thought reasoning L Ranaldi, A Freitas Proceedings of the 18th Conference of the European Chapter of the …, 2024 | 17 | 2024 |
Lacking the embedding of a word? look it up into a traditional dictionary ES Ruzzetti, L Ranaldi, M Mastromattei, F Fallucchi, FM Zanzotto Findings of the Association for Computational Linguistics: ACL 2022, 2022 | 15 | 2022 |
The Dark Side of the Language: Pre-trained Transformers in the DarkNet L Ranaldi, A Nourbakhsh, A Patrizi, ES Ruzzetti, D Onorati, F Fallucchi, ... Proceedings of the 14th International Conference on Recent Advances in …, 2023 | 14 | 2023 |
Empowering cross-lingual abilities of instruction-tuned large language models by translation-following demonstrations L Ranaldi, G Pucci, A Freitas Findings of the Association for Computational Linguistics ACL 2024, 7961–7973, 2023 | 12 | 2023 |
Syntax and prejudice: Ethically-charged biases of a syntax-based hate speech recognizer unveiled M Mastromattei, L Ranaldi, F Fallucchi, FM Zanzotto PeerJ Computer Science 8, e859, 2022 | 12 | 2022 |
Does the English matter? elicit cross-lingual abilities of large language models L Ranaldi, G Pucci Proceedings of the 3rd Workshop on Multi-lingual Representation Learning …, 2023 | 11 | 2023 |
CryptoNet: Using Auto-Regressive Multi-Layer Artificial Neural Networks to Predict Financial Time Series L Ranaldi, M Gerardi, F Fallucchi Information 13 (11), 524, 2022 | 11 | 2022 |
Hiding Your Face Is Not Enough: user identity linkage with image recognition FMZ Leondardo Ranaldi Social Network Analysis and Mining 10 (1), 1-9, 2020 | 10 | 2020 |
PreCog: Exploring the relation between memorization and performance in pre-trained language models L Ranaldi, ES Ruzzetti, FM Zanzotto Proceedings of the 14th International Conference on Recent Advances in …, 2023 | 9 | 2023 |
A Tree-of-Thoughts to Broaden Multi-step Reasoning across Languages L Ranaldi, G Pucci, F Ranaldi, ES Ruzzetti, FM Zanzotto Findings of the Association for Computational Linguistics: NAACL 2024, 1229-1241, 2024 | 8* | 2024 |
KERMITviz: Visualizing Neural Network Activations on Syntactic Trees L Ranaldi, F Fallucchi, A Santilli, FM Zanzotto Research Conference on Metadata and Semantics Research, 139-147, 2021 | 8 | 2021 |
Shedding light on the dark web: Authorship attribution in radical forums L Ranaldi, F Ranaldi, F Fallucchi, FM Zanzotto Information 13 (9), 435, 2022 | 7 | 2022 |
Modeling easiness for training transformers with curriculum learning L Ranaldi, G Pucci, FM Zanzotto Proceedings of the 14th International Conference on Recent Advances in …, 2023 | 6 | 2023 |
Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation F Ranaldi, ES Ruzzetti, D Onorati, L Ranaldi, C Giannone, A Favalli, ... Findings of the Association for Computational Linguistics: ACL 2024, 2024 | 5 | 2024 |
Pat-in-the-Loop: Declarative Knowledge for Controlling Neural Networks D Onorati, P Tommasino, L Ranaldi, F Fallucchi, FM Zanzotto Future Internet 12 (12), 218, 2020 | 5 | 2020 |