Samuele Punzo

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

Tue, 31 Mar 2026 00:00:00 +0000

This paper introduces a simple, principled interpretability framework based on token-level perplexity to test whether LLMs rely on linguistically relevant cues when solving benchmarks.

Key contributions:

A hypothesis-driven analysis method using perplexity distributions over minimal sentence pairs
No reliance on unstable feature-attribution techniques
Experiments on controlled linguistic benchmarks with several open-weight LLMs
Evidence that linguistically important tokens influence but never fully explain model behavior, revealing reliance on non-linguistic heuristics

Machine Learning for analysis of Multiple Sclerosis cross-tissue bulk and single-cell transcriptomics data

Thu, 05 Mar 2026 00:00:00 +0000

This paper presents an integrative approach combining multi-omics data (Microarray and scRNA-seq) with explainable machine learning methods for the discovery of pathway-level signatures in Multiple Sclerosis.

Key contributions:

Cross-tissue integration of bulk and single-cell transcriptomics data
Explainable ML pipeline for pathway-level biomarker identification
Comparison of Microarray integration methods (ComBat, XPN)
Biological enrichment analysis for pathway discovery

A Machine Learning Pipeline for Multiple Sclerosis Biomarker Discovery: Comparing explainable AI and Traditional Statistical Approaches

Fri, 26 Sep 2025 00:00:00 +0000

This paper presents a comprehensive machine learning pipeline for biomarker discovery in Multiple Sclerosis, comparing explainable AI methods (SHAP, LIME) with traditional statistical approaches. The pipeline was applied to Microarray and scRNA-seq transcriptomics data, evaluating different feature selection and interpretation strategies.

Key contributions:

Systematic comparison of XAI-based vs. statistical biomarker identification
Integration of multiple data modalities (Microarray, scRNA-seq)
Biological validation through enrichment analysis tools (DAVID, StringDB, Cytoscape)

CIBB25 — Conference Presentation

Wed, 01 Jan 2025 00:00:00 +0000

Conference presentation of the paper: “ML Pipeline for Multiple Sclerosis Biomarker Discovery: XAI vs. Statistical Approaches” (arXiv: 2509.22484).

BBCC24 — Conference Presentation

Fri, 01 Nov 2024 00:00:00 +0000

Conference presentation of the paper: “ML Pipeline for Multiple Sclerosis Biomarker Discovery: XAI vs. Statistical Approaches” (arXiv: 2509.22484).

Bologna Orthogonal Summer Term '24

Thu, 01 Aug 2024 00:00:00 +0000

Intensive 2-week summer school covering advanced topics in machine learning theory and biomedical applications. Organised by Fondazione ELICSIR and fully funded for selected top Italian STEM students.

Futuro Annunciato '24

Mon, 01 Jul 2024 00:00:00 +0000

Intensive 3-day programme exploring frontiers of Computer Science, organised by Fondazione ELICSIR and sponsored by Schmidt Sciences.