Picture for Fabio Massimo Zanzotto

Fabio Massimo Zanzotto

University of Rome-Tor Vergata

Linguistic Fingerprint in Transformer Models: How Language Variation Influences Parameter Selection in Irony Detection

Jun 04, 2024
Viaarxiv icon

Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation

Add code
Feb 12, 2024
Figure 1 for Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation
Figure 2 for Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation
Figure 3 for Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation
Figure 4 for Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation
Viaarxiv icon

Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models

Add code
Feb 05, 2024
Viaarxiv icon

Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts

Nov 14, 2023
Figure 1 for Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
Figure 2 for Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
Figure 3 for Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
Figure 4 for Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
Viaarxiv icon

HANS, are you clever? Clever Hans Effect Analysis of Neural Systems

Sep 21, 2023
Figure 1 for HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
Figure 2 for HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
Figure 3 for HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
Figure 4 for HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
Viaarxiv icon

A Trip Towards Fairness: Bias and De-Biasing in Large Language Models

May 23, 2023
Figure 1 for A Trip Towards Fairness: Bias and De-Biasing in Large Language Models
Figure 2 for A Trip Towards Fairness: Bias and De-Biasing in Large Language Models
Figure 3 for A Trip Towards Fairness: Bias and De-Biasing in Large Language Models
Figure 4 for A Trip Towards Fairness: Bias and De-Biasing in Large Language Models
Viaarxiv icon

PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models

May 09, 2023
Figure 1 for PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
Figure 2 for PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
Figure 3 for PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
Viaarxiv icon

Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages

May 03, 2023
Figure 1 for Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages
Figure 2 for Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages
Figure 3 for Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages
Figure 4 for Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages
Viaarxiv icon

The Dark Side of the Language: Pre-trained Transformers in the DarkNet

Add code
Feb 09, 2022
Figure 1 for The Dark Side of the Language: Pre-trained Transformers in the DarkNet
Figure 2 for The Dark Side of the Language: Pre-trained Transformers in the DarkNet
Figure 3 for The Dark Side of the Language: Pre-trained Transformers in the DarkNet
Viaarxiv icon

Every time I fire a conversational designer, the performance of the dialog system goes down

Sep 27, 2021
Figure 1 for Every time I fire a conversational designer, the performance of the dialog system goes down
Figure 2 for Every time I fire a conversational designer, the performance of the dialog system goes down
Figure 3 for Every time I fire a conversational designer, the performance of the dialog system goes down
Figure 4 for Every time I fire a conversational designer, the performance of the dialog system goes down
Viaarxiv icon