Giovanni Delnevo

Artificial intelligence (AI) and large language models are powerful tools but come with risks and caveats for proper usage. In this work, we are concerned with effective human-AI collaboration. As in any team, it is key that all team members properly understand the problem at hand, the environment, and each other. In order to scaffold a mature human-AI collaboration, we propose a process framework based on continual, proactive, bidirectional assessment, fostering co-evolution of the human-AI team. While most research has focused on assessing the strengths and limitations of AI agents, we especially focus on the risks associated with a lack of maturity on the human side. The core idea is to have AI agents help humans assess themselves and to anticipate interaction issues. Furthermore, to place the proposal within a broader vision, we advance two novel concepts: (i) “AI-in-the-human-loop”, the idea of AI agents observing and acting within human reasoning and activity, and (ii) “human-under-test”, a software testing analogy that suggests techniques for assessing human maturity by AI agents. A case study of a human-AI team involved in a statistical analysis project is considered, and analysed through an LLM-as-a-judge setup. Preliminary results highlight collaboration maturity issues and the possibility of proactive corrections, showcasing limitations in current collaborative workflows and opportunities for further research.

Communicating complex environmental phenomena requires forms of visualization that go beyond analytical accuracy to support engagement, interpretation, and reflection. Eco-visualization addresses this challenge by combining data representation with aesthetic and narrative elements, but its creation often demands technical skills. This paper presents a Human–AI co-creative pipeline for the design of eco-visualizations, in which AI acts as an active collaborator throughout the visual creation process. The approach integrates generative image creation, AI-assisted segmentation, and data-driven color mapping into a structured workflow that supports iterative interaction between human and AI. We implement this pipeline as a web-based system and evaluate it through a user study with a mixed-method approach. Results show that while the system is perceived as engaging and conceptually innovative, users experience notable usability challenges and cognitive load during interaction. These findings highlight key tensions in Human–AI co-creation, particularly between control and ease of use. Overall, this work contributes a concrete design approach to Human–AI collaboration in eco-visualization and provides empirical insights that inform the development of more accessible and effective co-creative tools for communicating complex environmental data.

User-Centered Design (UCD) relies on the active involvement of end users throughout the design process. However, in complex socio-technical domains, continuous user participation is often difficult to sustain due to time constraints, safety requirements, confidentiality issues, high workload, or limited access to operational environments. This conceptual paper proposes an Agentic UCD framework based on Large Language Model (LLM) User Twins (UTs) to address this user involvement gap. UTs are proposed as generative, interactive, adaptive, and agentic representations of target users or user groups, grounded in user research, domain knowledge, task descriptions, scenarios, and design constraints. Unlike traditional personas, which make user knowledge explicit but remain static, UTs can be queried, updated, and reused across design activities. Within the proposed framework, UTs support design exploration, implementation, synthetic evaluation, and preparation for human validation by acting as role-oriented agents that simulate user perspectives, critique design alternatives, generate scenarios, and identify potential usability, trust, workload, or accessibility issues. The paper emphasizes that UTs do not replace empirical user research, co-design, or usability testing. Their outputs should be treated as simulated feedback and design hypotheses, not as empirical evidence. Instead, UTs are positioned as a complementary mechanism for maintaining continuity in user-centered reasoning between moments of direct user involvement.

The increasing adoption of Large Language Models (LLMs) in software development has enabled automatic code generation from natural language, yet the influence of communicative factors such as prompt tone remains underexplored. This work introduces PromptTone, a controlled dataset designed to investigate how variations in prompt politeness affect LLM-based code generation in web development. The dataset is constructed through a structured experimental design combining three variables: programming paradigm (Vue.js Composition API vs. Options API), LLM provider (GPT, Claude, Gemini), and prompt tone (impolite, neutral, polite), resulting in 396 generated components across 22 implementations. Data were collected in an educational setting under a single-prompt constraint to capture first-shot model behavior, and are provided in both hierarchical and CSV formats, including prompts, generated code, and error annotations. Preliminary analysis reveals that prompt tone influences output characteristics such as verbosity, with model-specific patterns: for instance, some models exhibit increased output length with more polite prompts, while others remain stable. Differences also emerge across programming paradigms, suggesting an interaction between tone and code structure. These findings highlight that LLMs are sensitive not only to semantic content but also to pragmatic aspects of input. Overall, the dataset provides a novel benchmark for studying human–LLM interaction in code generation, supporting future research on prompt engineering, model evaluation, and socially-aware Artificial Intelligence (AI)-assisted development tools.

As data visualizations become increasingly central to communication, analysis, and decision-making across a variety of fields, the need to ensure their accessibility becomes critical. Visual representations, such as charts, graphs, and infographics, are effective tools for conveying complex information; however, they often present significant barriers for individuals with various types of impairments. This paper explores the potential of Machine Learning (ML) to enhance the accessibility of data visualizations. Specifically, we present a Systematic Literature Review (SLR) that investigates how ML techniques have been applied to make visual data more inclusive. The review considers both visualization-related aspects (such as visualization types and source, target user, and evaluation) and ML-related factors (including data formats, preprocessing, and model types and evaluation). Our findings reveal that only a limited number of studies directly address the use of ML for improving visualization accessibility, and there is a lack of standardized solutions or frameworks in this area. Our contribution focused on the identification of a conceptual framework based on nine key open challenges that highlight the lack of consideration for infographics, particular types of charts, printed chart, different kind of impairments, involvement of users, accurate interpretation of complex visual data, real-time support, standard benchmarking, the potential bias and, hence, the need for continued research and development at the intersection of data visualization and machine learning, with a strong focus on accessibility and inclusivity.