9 citations · 22 across the 13 of their papers we have counts for
14 papers
LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
Mohan Li, Chengyu Yu, Francesco Sovrano +2
Large Language Model (LLM) alignment is intended to ensure that models remain helpful and safe, but its stability under input distributional shift is not yet fully understood. Prio…
Security and Privacy in Agentic AI: Grand Challenges and Future Directions
Adam Jenkins, Agnieszka Kitkowska, Caterina Maidhof +22
We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading intern…
SALT-GNN: Handling Dense Neighborhoods in Anti-Money Laundering Graphs via Statistics-Aware Attention
Lidia Losavio, Francesco Sovrano, Dario Fenoglio +2
Money laundering threatens financial stability and exposes institutions to penalties, motivating automated detection. Because laundering schemes often emerge through relational pat…
Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation
Francesco Sovrano, Gabriele Dominici, Marc Langheinrich
A central goal of explainable AI is to express large language model (LLM) decision logic symbolically and ground it in internal mechanisms. Existing rule-extraction methods usually…
Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering
Francesco Sovrano, Gabriele Dominici, Alberto Bacchelli
Prompt-induced cognitive biases are changes in a general-purpose AI (GPAI) system's decisions caused solely by biased wording in the input (e.g., framing, anchors), not task logic.…
Assessing Model-Agnostic XAI Methods against EU AI Act Explainability Requirements
Francesco Sovrano, Giulia Vilone, Michael Lognoul
Explainable AI (XAI) has evolved in response to expectations and regulations, such as the EU AI Act, which introduces regulatory requirements on AI-powered systems. However, a pers…
Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models
Francesco Sovrano, Alberto Bacchelli
Natural language explanations produced by large language models (LLMs) are often persuasive, but not necessarily scrutable: users cannot easily verify whether the claims in an expl…
In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks
Francesco Sovrano, Lidia Losavio, Giulia Vilone +1
Symbolic regression aims to replace black-box predictors with concise analytical expressions that can be inspected and validated in scientific machine learning. Kolmogorov-Arnold N…
Detecting Semantic Clones of Unseen Functionality
Konstantinos Kitsios, Francesco Sovrano, Earl T. Barr +1
Semantic code clone detection is the task of detecting whether two snippets of code implement the same functionality (e.g., Sort Array). Recently, many neural models achieved near-…
Is General-Purpose AI Reasoning Sensitive to Data-Induced Cognitive Biases? Dynamic Benchmarking on Typical Software Engineering Dilemmas
Francesco Sovrano, Gabriele Dominici, Rita Sevastjanova +2
Human cognitive biases in software engineering can lead to costly errors. While general-purpose AI (GPAI) systems may help mitigate these biases due to their non-human nature, thei…
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP
Francesco Sovrano
Large language models (LLMs) can amplify misinformation, undermining societal goals such as the UN SDGs. We study three documented drivers of misinformation (valence framing, infor…
Large Language Models for In-File Vulnerability Localization Can Be "Lost in the End"
Francesco Sovrano, Adam Bauer, Alberto Bacchelli
Recent advancements in artificial intelligence have enabled processing of larger inputs, leading everyday software developers to increasingly rely on chat-based large language mode…
Aligning XAI with EU Regulations for Smart Biomedical Devices: A Methodology for Compliance Analysis
Francesco Sovrano, Michael Lognoul, Giulia Vilone
Significant investment and development have gone into integrating Artificial Intelligence (AI) in medical and healthcare applications, leading to advanced control systems in medica…
An Empirical Study on Compliance with Ranking Transparency in the Software Documentation of EU Online Platforms
Francesco Sovrano, Michaël Lognoul, Alberto Bacchelli
Compliance with the European Union's Platform-to-Business (P2B) Regulation is challenging for online platforms, and assessing their compliance can be difficult for public authoriti…