Author

Samuele Punzo

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Jul 2026

Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept

Distinguishing animate from inanimate concepts in written language requires more than shallow text processing, as it involves recognizing complex selectional constraints and contextual cues, such as verb-argument interactions. Yet, current large language models (LLMs) appear to be capable of doing it. We investigate wh...

Samuele Punzo, Giovanni Ciná, Sandro Pezzelle · arXiv.org · 0 citations

#natural language process... Mar 2026

Is my model perplexed for the right reason? Contrasting LLMs' Benchmark Behavior with Token-Level Perplexity

A simple, principled interpretability framework based on token-level perplexity to test whether models rely on linguistically relevant cues is introduced, revealing that models rely on heuristics other than the expected linguistic ones.

Zoë Prins, Samuele Punzo, Frank Wildenburg et al. · arXiv.org · 1 citation

#artificial intelligence Preprint Jun 2026

How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms

The results suggest that intuitive-physics knowledge emerges reliably in pretrained video representations, but its accessibility depends strongly on pretraining paradigm, representational depth, and readout mechanism.

Samuele Punzo, N. Caselli, Ippokratis Pantelidis et al. · 3 citations