Elisabetta Rocchetti

Orcid: 0009-0000-5617-7612

According to our database1, Elisabetta Rocchetti authored at least 10 papers between 2023 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism.
CoRR, April, 2026

2025
Modeling Transformers as complex networks to analyze learning dynamics.
CoRR, September, 2025

How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis.
CoRR, September, 2025

What's Taboo for You? - An Empirical Evaluation of LLMs Behavior Toward Sensitive Content.
CoRR, July, 2025

Processing and Representation of Linguistic Properties in Large Language Models.
Proceedings of the 33nd Symposium on Advanced Database Systems, 2025

The Cow of Rembrandt Analyzing Artistic Prompt Interpretation in Text-to-Image Models.
Proceedings of the 35th IEEE International Workshop on Machine Learning for Signal Processing, 2025

2024
Unveiling Transformer Perception by Exploring Input Manifolds.
CoRR, 2024

Causal Mediation Analysis for Interpreting Large Language Models.
Proceedings of the 32nd Symposium of Advanced Database Systems, 2024

2023
Augustine of Hippo at SemEval-2023 Task 4: An Explainable Knowledge Extraction Method to Identify Human Values in Arguments with SuperASKE.
Proceedings of the The 17th International Workshop on Semantic Evaluation, 2023

A Discussion on Open Issues Regarding Human Value Detection in Arguments.
Proceedings of the 31st Symposium of Advanced Database Systems, 2023


  Loading...