Picture for Pietro Bernardelle

Pietro Bernardelle

Spotting Persuasion: A Low-cost Model for Persuasion Detection in Political Ads on Social Media

Add code
Mar 18, 2025
Viaarxiv icon

SubData: A Python Library to Collect and Combine Datasets for Evaluating LLM Alignment on Downstream Tasks

Add code
Dec 21, 2024
Viaarxiv icon

Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas

Add code
Dec 19, 2024
Figure 1 for Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas
Figure 2 for Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas
Figure 3 for Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas
Figure 4 for Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas
Viaarxiv icon

Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective

Add code
Oct 22, 2024
Figure 1 for Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective
Figure 2 for Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective
Figure 3 for Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective
Figure 4 for Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective
Viaarxiv icon