Abstract
Large language model (LLM)-powered assistants are increasingly used for generating program code and unit tests, but their application in acceptance testing remains underexplored. To help address this gap, this paper explores the use of LLMs for generating executable acceptance tests for web applications through a two-step process: (i) generating acceptance test scenarios in natural language (in Gherkin) from user stories, and (ii) converting these scenarios into executable test scripts (in Cypress), knowing the HTML code of the pages under test. This two-step approach supports acceptance test-driven development, enhances tester control, and improves test quality. The two steps were implemented in the AutoUAT and Test Flow tools, respectively, powered by GPT-4 Turbo, and integrated into a partner company's workflow and evaluated on real-world projects. The users found the acceptance test scenarios generated by AutoUAT helpful 95% of the time, even revealing previously overlooked cases. Regarding Test Flow, 92% of the acceptance test cases generated by Test Flow were considered helpful: 60% were usable as generated, 8% required minor fixes, and 24% needed to be regenerated with additional inputs; the remaining 8% were discarded due to major issues. These results suggest that LLMs can, in fact, help improve the acceptance test process, with appropriate tooling and supervision.

Abstract
Recent advancements in deep learning and large language models (LLMs) have led to the development of innovative technologies that enhance recommender systems. Different heuristics, architectures, and techniques for filtering information have been proposed to obtain successful computational models for the recommendation problem; however, several issues must be addressed in online environments. This research focuses on a specific type of recommendation, which combines sequential recommendation with session-based recommendation. The goal is to solve the complex next-item recommendation problem in Web applications, using the wine domain as a case study. This paper describes a framework developed to provide adaptive recommendations by rethinking the initial data modeling to better understand users' dynamic taste profiles. Three main contributions are presented: (a) a novel dataset of wines called X-Wines; (b) an updated recommendation model named X-Model4Rec – eXtensible Model for Recommendation, which utilizes attention and transformer mechanisms central to LLMs; and (c) a collaborative Web platform designed to support adaptive wine recommendations for users in an online environment. The results indicate that the proposed framework can enhance recommendations in online environments and encourage further scientific exploration of this topic.   Received: 15 December 2024 | Revised: 12 June 2025 | Accepted: 30 June 2025   Conflicts of Interest The authors declare that they have no conflicts of interest to this work.   Data Availability Statement The data that support the findings of this study are openly available in X-Wines Research Project at https://sites.google.com/farroupilha.ifrs.edu.br/xwines.   Author Contribution Statement Rogério Xavier de Azambuja: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, and Project administration. A. Jorge Morais: Conceptualization, Methodology, Validation, Formal analysis, Data curation, Writing – review & editing, Visualization, Supervision, and Project administration. Vítor Filipe: Conceptualization, Methodology, Validation, Formal analysis, Data curation, Writing – review & editing, Visualization, and Project administration.

Abstract

Abstract

Abstract
With the proliferation of ODR service providers, there is a critical necessity to establish mechanisms supporting their functioning, particularly while designing ODR processes. This article aims to examine the impact of process modelling using BPMN, and of its relevance in the integration of AI into ODR processes within the EU. BPMN allows a meticulous depiction of all the ODR process steps, stakeholders, and underlying data in structured formats that are readable and interpretable by both humans and AI, which enables its integration. The advantages include predictive analysis, identification of opportunities for continuous improvement, operational efficiency, cost and time reduction, and enhanced accessibility for self-represented litigants. Additionally, the transparency afforded by explicitly incorporating AI in BPMN notation fosters a clearer comprehension of processes, facilitating management and informed decision-making. Nevertheless, it remains imperative to address ethical concerns such as algorithmic bias, fairness, and privacy.

Abstract
Leveraging the capabilities of Knowledge Distillation (KD) strategies, we devise a strategy to fight the recent retraction of face recognition datasets. Given a pretrained Teacher model trained on a real dataset, we show that carefully utilising synthetic datasets, or a mix between real and synthetic datasets to distil knowledge from this teacher to smaller students can yield surprising results. In this sense, we trained 33 different models with and without KD, on different datasets, with different architectures and losses. And our findings are consistent, using KD leads to performance gains across all ethnicities and decreased bias. In addition, it helps to mitigate the performance gap between real and synthetic datasets. This approach addresses the limitations of synthetic data training, improving both the accuracy and fairness of face recognition models.