Gabriele Sarti

Latest

• Interpretability for Language Models: Current Trends and Applications
• Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses
• Interpreting Context Usage in Generative Language Models with Inseq, PECoRe and MIRAGE
• Multi-property Steering of Large Language Models with Dynamic Activation Composition
• Interpreting Context Usage in Generative Language Models with Inseq and PECoRe
• IT5: Text-to-text Pretraining for Italian Language Understanding and Generation
• Quantifying the Plausibility of Context Reliance in Neural Machine Translation
• A Primer on the Inner Workings of Transformer-based Language Models
• Quantifying the Plausibility of Context Reliance in Neural Machine Translation
• Post-hoc Interpretability for Generative Language Models: Explaining Context Usage in Transformers
• Explaining Language Models with Inseq
• Post-hoc Interpretability for Language Models
• DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
• Quantifying the Plausibility of Context Reliance in Neural Machine Translation
• Post-hoc Interpretability for NLG & Inseq: an Interpretability Toolkit for Sequence Generation Models
• Post-hoc Interpretability for Neural Language Models
• Explaining Neural Language Models from Internal Representations to Model Predictions
• RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation
• Post-hoc Interpretability for Neural Language Models
• Inseq: An Interpretability Toolkit for Sequence Generation Models
• Advanced XAI Techniques and Inseq: An Interpretability Toolkit for Sequence Generation Models
• Introducing Inseq: An Interpretability Toolkit for Sequence Generation Models
• Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation
• Inseq: An Interpretability Toolkit for Sequence Generation Models
• Attributing Context Usage in Language Models
• Inseq: An Interpretability Toolkit for Sequence Generation Models
• Towards User-centric Interpretability of Machine Translation Models
• Probing Linguistic Knowledge in Italian Neural Language Models across Language Varieties
• DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages
• Towards User-centric Interpretability of NLP Models
• Empowering Human Translators via Interpretable Interactive Neural Machine Translation
• Characterizing Linguistic Complexity in Humans and Language Models
• Contrastive Language-Image Pre-training for the Italian Language
• Contrastive Image-Text Pretraining for Italian
• Teaching NLP with Bracelets and Restaurant Menus: An Interactive Workshop for Italian Students
• That Looks Hard: Characterizing Linguistic Complexity in Humans and Language Models
• Interpreting Neural Language Models for Linguistic Complexity Assessment
• UmBERTo-MTSA@ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations
• ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation
• ICLR 2020 Trends: Better & Faster Transformers for Natural Language Processing
• Covid-19 Semantic Browser
• Neural Language Models: the New Frontier of Natural Language Understanding
• The Literary Ordnance: When the Writer is an AI
• AItalo Svevo: Letters from an Artificial Intelligence
• Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
• Histopathologic Cancer Detection with Neural Networks