Large Language Models (LLMs) are increasingly integrated into software engineering (SE) tools for tasks that extend beyond code synthesis, including judgment under uncertainty and reasoning in ethically significant contexts. We present a fully automated framework for assessing ethical reasoning capabilities across 16 LLMs in a zero-shot setting, using 30 real-world ethically charged scenarios. Each model is prompted to identify the most applicable ethical theory to an action, assess its moral acceptability, and explain the reasoning behind their choice. Responses are compared against expert ethicists’ choices using inter-model agreement metrics. Our results show that LLMs achieve an average Theory Consistency Rate (TCR) of 73.3% and Binary Agreement Rate (BAR) on moral acceptability of 86.7%, with interpretable divergences concentrated in ethically ambiguous cases. A qualitative analysis of free-text explanations reveals strong conceptual convergence across models despite surface-level lexical diversity. These findings support the potential viability of LLMs as ethical inference engines within SE pipelines, enabling scalable, auditable, and adaptive integration of user-aligned ethical reasoning. Our focus is the Ethical Interpreter component of a broader profiling pipeline: we evaluate whether current LLMs exhibit sufficient interpretive stability and theory-consistent reasoning to support automated profiling.

Abstract Protecting privacy and ethics of citizens is among the core concerns raised by an increasingly digital society. Profiling users is common practice for software applications triggering the need for users, also enforced by laws, to manage privacy settings properly. Users need to properly manage these settings to protect personally identifiable information and express personal ethical preferences. This has shown to be very difficult for several concurrent reasons. However, profiling technologies can also empower users in their interaction with the digital world by reflecting personal ethical preferences and allowing for automatizing/assisting users in privacy settings. In this way, if properly reflecting users’ preferences, privacy profiling can become a key enabler for a trustworthy digital society. We focus on characterizing/collecting users’ privacy preferences and contribute a step in this direction through an empirical study on an existing dataset collected from the fitness domain. We aim to understand which set of questions is more appropriate to differentiate users according to their privacy preferences. The results reveal that a compact set of semantic-driven questions (about domain-independent privacy preferences) helps distinguish users better than a complex domain-dependent one. Based on the outcome, we implement a recommender system to provide users with suitable recommendations related to privacy choices. We then show that the proposed recommender system provides relevant settings to users, obtaining high accuracy.

Abstract Autonomous robots can be employed in exploring unknown environments and performing many tasks, such as, e.g. detecting areas of interest, collecting target objects, etc. Deep reinforcement learning (RL) is often used to train this kind of robot. However, concerning the artificial environments aimed at testing the robot, there is a lack of available data sets and a long time is needed to create them from scratch. A good data set is in fact usually produced with high effort in terms of cost and human work to satisfy the constraints imposed by the expected results. In the first part of this paper, we focus on the specification of the properties of the solutions needed to build a data set, making the case of environment exploration. In the proposed approach, rather than using imperative programming, we explore the possibility of generating data sets using constraint programming in Prolog. In this phase, geometric predicates describe a virtual environment according to inter-space requirements. The second part of the paper is focused on testing the generated data set in an AI gym via space search techniques. We developed a Neuro-Symbolic agent built from the following: (i) A deep Q-learning component implemented in Python, able to address via RL a search problem in the virtual space; the agent has the goal to explore a generated virtual environment to seek for a target, improving its performance through a RL process. (ii) A symbolic component able to re-address the search when the Q-learning component gets stuck in a part of the virtual environment; these components stimulate the agent to move to and explore other parts of the environment. Wide experimentation has been performed, with promising results, and is reported, to demonstrate the effectiveness of the approach.

Software companies have an interest in reaching the maximum amount of potential customers while, at the same time, providing a frictionless experience. Desktop web app frameworks are promising in this respect, allowing developers and companies to reuse existing code and knowledge of web applications to create cross-platform apps integrated with native APIs. Despite their growing popularity, existing challenges in employing these technologies have not been documented, and it is hard for individuals and companies to weigh benefits and pros against drawbacks and cons.In this paper, we address this issue by investigating the challenges that developers frequently experience when adopting desktop web app frameworks. To achieve this goal, we mine and apply topic modeling techniques to a dataset of 10,822 Stack Overflow posts related to the development of desktop web applications. Analyzing the resulting topics, we found that: i) developers often experience issues regarding the build and deployment processes for multiple platforms; ii) reusing existing libraries and development tools in the context of desktop applications is often cumbersome; iii) it is hard to solve issues that arise when interacting with native APIs. Furthermore, we confirm our finding by providing evidence that the identified issues are also present in the issue reports of 453 open-source applications publicly hosted on GitHub.