Picture for Andrea Seveso

Andrea Seveso

SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs

Add code
Mar 04, 2025
Viaarxiv icon

Designing Role Vectors to Improve LLM Inference Behaviour

Add code
Feb 17, 2025
Viaarxiv icon

XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models

Add code
Jul 21, 2024
Figure 1 for XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models
Figure 2 for XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models
Viaarxiv icon

Disce aut Deficere: Evaluating LLMs Proficiency on the INVALSI Italian Benchmark

Add code
Jun 25, 2024
Viaarxiv icon