arXiv subjects

Matteo Silvestri

Publications and source records attributed to Matteo Silvestri.

10 recordsLinked to original sources

arXiv2026

Explaining AI Agents Through Execution Traces

AI Agents are increasingly deployed in real-world settings, where they interact with external tools and make sequential decisions with limited human oversight. This creates a pressing need for reliable and auditable explanations of what an agent did and why. However, traditional Explainable AI (XAI) methods fall short of providing the process-level transparency required for such interactive, multi-step systems, motivating a paradigm shift toward approaches specifically designed for AI Agents. To address this gap, we present a post-hoc XAI framework that transforms a lengthy agent's execution trace into a structured report and a faithful natural-language explanation explicitly grounded in its observable behavior. Because it relies solely on execution traces, the framework applies across different agent architectures, environments, and tasks. Human and automated evaluations across multiple benchmarks and architectures show that our framework produces high-quality, trace-faithful explanations while reliably identifying unsupported claims, unjustified actions, and evidence gaps, outperforming naive LLM-generated explanations.

cs.AI↗

arXiv2026

EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents

The web is increasingly accessed by AI agents rather than humans. Every agent needs knowledge, especially in the life-sciences, where agentic pipelines are growing fast. Access to the literature is a crucial part of that need, and resources such as Europe PMC, with over 40M indexed records, are widely used to meet it. Yet these resources were not built for AI agents: they take keywords and complex syntax and return whole papers, so every agent must learn the syntax, issue several searches, and read full papers to find the evidence it needs. We introduce EMBL AI Librarian, a knowledge layer that upgrades the Europe PMC interface for AI agents: an agent asks in natural language and receives evidence that answers it. A single LLM orchestrates the whole knowledge retrieval process: it plans complementary subqueries executed by the live Europe PMC search engine, then reads the selected papers and locates the relevant evidence. We evaluate Librarian across four benchmarks: literature synthesis, claim verification, open-domain question answering, and downstream biology tasks such as protocol questions and sequence manipulation. On ScholarQABench, Librarian improves Citation F1 by more than $16$ points over strong recently published baselines. Used as the retrieval layer of an existing claim-verification pipeline, it increases agreement with expert consensus; and on the open-form LitQA2 benchmark, a GPT-5.4 agent scores about $8$ points higher when grounded in Librarian than with web search. Overall, our results show that equipping life-science agents with the Librarian knowledge layer improves performance across a range of tasks. We release our code publicly at https://github.com/petroni-lab/librarian

cs.CL↗

arXiv2026

Enantio-selective inverse Faraday effect in isotropic chiral molecular mixtures

Enantiomeric excess detection in a chiral molecular mixture is paramount because very often opposite enantiomers exhibit profound functional dissimilarities that play decisive roles in biochemical applications. Existing chiral sensing methods mostly rely on large operational sample volumes, hindering compatibility with integrated sensing schemes. Here, we propose a novel chiroptical sensing technique based on the inverse Faraday effect in a photonic micro-capillary filled with nl-volume chiral drug solution. We theoretically demonstrate that, upon excitation by intense laser light, an isotropic assembly of chiral drugs produces a static magnetisation, with amplitude and direction depending on the enantiomeric excess. In turn, by measuring the chirally-sensitive static magnetic field in the vicinity of the micro-tube one can retrieve the enantiomeric excess of the chiral drug solution. Our theoretical predictions unlock new opportunities for the development of innovative nanophotonic devices suitable for efficient chiroptical sensing with nl-volume sensitivity.

physics.optics↗

arXiv2026

PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations

Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a one-size-fits-all paradigm that neglects user differences in expertise, goals, and cognitive needs. Although Large Language Models can translate technical explanations into natural language, they introduce challenges related to faithfulness and hallucinations. To address these challenges, we present PONTE (Personalized Orchestration for Natural language Trustworthy Explanations), a human-in-the-loop framework for adaptive and reliable XAI narratives. PONTE models personalization as a closed-loop validation and adaptation process rather than prompt engineering. It combines: (i) a low-dimensional preference model capturing stylistic requirements; (ii) a preference-conditioned generator grounded in structured XAI artifacts; and (iii) verification modules enforcing numerical faithfulness, informational completeness, and stylistic alignment, optionally supported by retrieval-grounded argumentation. User feedback iteratively updates the preference state, enabling quick personalization. Automatic and human evaluations across healthcare and finance domains show that the verification-refinement loop substantially improves completeness and stylistic alignment over validation-free generation. Human studies further confirm strong agreement between intended preference vectors and perceived style, robustness to generation stochasticity, and consistently positive quality assessments.

cs.CL↗

arXiv2025

Femtosecond self-diffraction as a measure of the nonlinear response spectrum

Self diffraction is a four-wave mixing process proportional to the square modulus of third-order nonlinearity susceptibility $\chi^{(3)}$, which is related to the material's electronic and thermal properties. In this study, we investigate the wavelength dependence of the self-diffracted signal generated by a femtosecond pulsed laser in a dye solution to directly evaluate the electronic third-order nonlinear susceptibility spectrum. By accounting for absorption effects and phase matching conditions, we determine the $\vert\chi^{(3)}\vert$ for different concentrations. Experimental results complemented with theoretical predictions, show that in the low absorption and thin sample limits, the signal reproduce the $\vert\chi^{(3)}\vert$ spectral profile. These findings demonstrate the feasibility of measuring nonlinear susceptibility spectra arising solely from the bound-electronic response across a wide spectral range and for various compounds.

physics.optics↗

arXiv2025

When Large Language Models Know the Table: A Framework for Assessing Data Contamination in Tabular Datasets

Large language models (LLMs) are increasingly exposed to data contamination, i.e., performance gains driven by prior exposure of test datasets rather than generalization. However, in the context of tabular data, this problem is largely unexplored. Existing approaches primarily rely on memorization tests, which are too coarse to detect contamination. In contrast, we propose a framework for assessing contamination in tabular datasets by generating controlled queries and performing comparative evaluation. Given a dataset, we craft multiple-choice aligned queries that preserve task structure while allowing systematic transformations of the underlying data. These transformations are designed to selectively disrupt dataset information while preserving partial knowledge, enabling us to isolate performance attributable to contamination. We complement this setup with non-neural baselines that provide reference performance, and we introduce a statistical testing procedure to formally detect significant deviations indicative of contamination. Empirical results on eight widely used tabular datasets reveal clear evidence of contamination in four cases. These findings suggest that performance on downstream tasks involving such datasets may be substantially inflated, raising concerns about the reliability of current evaluation practices.

cs.CL↗

arXiv2025

Enhancing XAI Narratives through Multi-Narrative Refinement and Knowledge Distillation

Explainable Artificial Intelligence has become a crucial area of research, aiming to demystify the decision-making processes of deep learning models. Among various explainability techniques, counterfactual explanations have been proven particularly promising, as they offer insights into model behavior by highlighting minimal changes that would alter a prediction. Despite their potential, these explanations are often complex and technical, making them difficult for non-experts to interpret. To address this challenge, we propose a novel pipeline that leverages Language Models, large and small, to compose narratives for counterfactual explanations. We employ knowledge distillation techniques along with a refining mechanism to enable Small Language Models to perform comparably to their larger counterparts while maintaining robust reasoning abilities. In addition, we introduce a simple but effective evaluation method to assess natural language narratives, designed to verify whether the models' responses are in line with the factual, counterfactual ground truth. As a result, our proposed pipeline enhances both the reasoning capabilities and practical performance of student models, making them more suitable for real-world use cases.

cs.LG↗

arXiv2025

Evading Overlapping Community Detection via Proxy Node Injection

Protecting privacy in social graphs requires preventing sensitive information, such as community affiliations, from being inferred by graph analysis, without substantially altering the graph topology. We address this through the problem of \emph{community membership hiding} (CMH), which seeks edge modifications that cause a target node to exit its original community, regardless of the detection algorithm employed. Prior work has focused on non-overlapping community detection, where trivial strategies often suffice, but real-world graphs are better modeled by overlapping communities, where such strategies fail. To the best of our knowledge, we are the first to formalize and address CMH in this setting. In this work, we propose a deep reinforcement learning (DRL) approach that learns effective modification policies, including the use of proxy nodes, while preserving graph structure. Experiments on real-world datasets show that our method significantly outperforms existing baselines in both effectiveness and efficiency, offering a principled tool for privacy-preserving graph modification with overlapping communities.

cs.SI↗

arXiv2025

The Right to Hide: Masking Community Affiliation via Minimal Graph Rewiring

Protecting privacy in social graphs may require obscuring nodes' membership in sensitive communities. However, doing so without significantly disrupting the underlying graph topology remains a key challenge. In this work, we address the community membership hiding problem, which involves strategically modifying the graph structure to conceal a target node's affiliation with a community, regardless of the detection algorithm used. We reformulate the original discrete, counterfactual graph search objective as a differentiable constrained optimisation task. To this end, we introduce $\nabla$-CMH, a new gradient-based method that operates within a feasible modification budget to minimise structural changes while effectively hiding a node's community membership. Extensive experiments on multiple datasets and community detection methods demonstrate that our technique outperforms existing baselines, achieving the best balance between node hiding effectiveness and graph rewiring cost, while preserving computational efficiency.

cs.SI↗

arXiv2024

Analysis of Hopfield Model as Associative Memory

This article delves into the Hopfield neural network model, drawing inspiration from biological neural systems. The exploration begins with an overview of the model's foundations, incorporating insights from mechanical statistics to deepen our understanding. Focusing on audio retrieval, the study demonstrates the Hopfield model's associative memory capabilities. Through practical implementation, the network is trained to retrieve different patterns.

cond-mat.dis-nn↗