activity
20202026
most citedDeep Neural Networks as Complex Networks

5 citations · 12 across the 19 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2025

Fixed Point Explainability

Emanuele La Malfa, Jon Vadillo, Marco Molinari +1

This paper introduces a formal notion of fixed point explanations, inspired by the "why regress" principle, to assess, through recursive applications, the stability of the interpla…

cs.LG2025

Out-of-Context Reasoning in Large Language Models

Jonathan Shaki, Emanuele La Malfa, Michael Wooldridge +1

We study how large language models (LLMs) reason about memorized knowledge through simple binary relations such as equality (), inequality (), and inclusion (). Unli…

cs.LG2025

Code Simulation as a Proxy for High-order Tasks in Large Language Models

Emanuele La Malfa, Christoph Weinhuber, Orazio Torre +6

Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. We coll…

cs.LG20251 cited

Jailbreaking Large Language Models in Infinitely Many Ways

Oliver Goldstein, Emanuele La Malfa, Felix Drinkall +2

We discuss the ``Infinitely Many Paraphrases'' attacks (IMP), a category of jailbreaks that leverages the increasing capabilities of a model to handle paraphrases and encoded commu…

cs.LG2024

Deep Neural Networks via Complex Network Theory: a Perspective

Emanuele La Malfa, Gabriele La Malfa, Giuseppe Nicosia +1

Deep Neural Networks (DNNs) can be represented as graphs whose links and vertices iteratively process data and solve tasks sub-optimally. Complex Network Theory (CNT), merging stat…

cs.LG2024

Code Simulation Challenges for Large Language Models

Emanuele La Malfa, Christoph Weinhuber, Orazio Torre +5

Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. This wo…