Gabriele Sarti

gsarti's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

authored a paper 4 months ago

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses

Paper • 2408.00584 • Published Aug 1 • 6

authored 2 papers 5 months ago

Multi-property Steering of Large Language Models with Dynamic Activation Composition

Paper • 2406.17563 • Published Jun 25 • 4

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation

Paper • 2406.13663 • Published Jun 19 • 7

authored a paper 7 months ago

A Primer on the Inner Workings of Transformer-based Language Models

Paper • 2405.00208 • Published Apr 30 • 9

authored 4 papers about 1 year ago

Quantifying the Plausibility of Context Reliance in Neural Machine Translation

Paper • 2310.01188 • Published Oct 2, 2023 • 1

ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation

Paper • 2008.10875 • Published Aug 25, 2020

RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation

Paper • 2305.17131 • Published May 26, 2023

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers

Paper • 2310.03686 • Published Oct 5, 2023 • 3

authored 5 papers over 1 year ago

Are Character-level Translations Worth the Wait? Comparing Character- and Subword-level Models for Machine Translation

Paper • 2302.14220 • Published Feb 28, 2023

Contrastive Language-Image Pre-training for the Italian Language

Paper • 2108.08688 • Published Aug 19, 2021 • 2

Inseq: An Interpretability Toolkit for Sequence Generation Models

Paper • 2302.13942 • Published Feb 27, 2023 • 1

IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation

Paper • 2203.03759 • Published Mar 7, 2022 • 5

DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages

Paper • 2205.12215 • Published May 24, 2022