NL2Vis (Natural Language to Visualization) is an emerging research area that involves interpreting natural language queries and translating them into visualizations that accurately represent the underlying data. It holds considerable potential for application, as it greatly facilitates data exploration for non-expert users. Following the growing use of generative AI in NL2Vis applications, we present V-RECS, the first LLM-based Visual Recommender augmented with explanations (E), captioning (C), and suggestions (S) to support further data exploration. V-RECS’ visualization narratives facilitate both response verification and data exploration by non-expert users. Furthermore, our proposed solution mitigates computational, controllability, and cost issues associated with using powerful LLMs by leveraging a methodology for effectively fine-tuning small models, such as LLama-2-7B. To generate insightful visualization narratives, we use Chain-of-Thoughts (CoT), a prompt engineering technique that helps LLMs identify and generate the logical steps to produce a correct answer. Since CoT is reported to perform poorly with small LMs, we adopted a strategy in which a large LLM (GPT-4), acting as a Teacher, generates CoT-based instructions to fine-tune a small model, Llama-2-7B, which plays the role of a Student. Extensive experiments - based on a framework for the quantitative evaluation of AI-based visualizations and on a manual assessment by a group of participants - show that V-RECS achieves performance scores comparable to GPT-4 at a much lower cost.

Visualization Recommendation Systems (VRSs) are a novel and challenging field of study aiming to help generate insightful visualizations from data and support non-expert users in information discovery. Among the many contributions proposed in this area, some systems embrace the ambitious objective of imitating human analysts to identify relevant relationships in data and make appropriate design choices to represent these relationships with insightful charts. We denote these systems as "agnostic" VRSs since they do not rely on human-provided constraints and rules but try to learn the task autonomously. Despite the high application potential of agnostic VRSs, their progress is hindered by several obstacles, including the absence of standardized datasets to train recommendation algorithms, the difficulty of learning design rules, and defining quantitative criteria for evaluating the perceptual effectiveness of generated plots. This article summarizes the literature on agnostic VRSs and outlines promising future research directions.

We present AnomalyByClick, an interactive visualization system that allows the monitoring and analysis of anomalies in the behavior of elderly patients during daily activities in a living environment.

Visualization recommendation is a novel and challenging field of study, whose aim is to provide non-expert users with automatic tools for insight discovery from data. Advances in this research area are hindered by the absence of reliable datasets on which to train the recommender systems. To the best of our knowledge, Plotly corpus is the only publicly available dataset, but as complained by many authors and discussed in this article, it contains many labeling errors, which greatly limits its usefulness. We release an improved version of the original dataset, named Plotly.plus, which we obtained through an automated procedure with minimal post-editing. In addition to a manual validation by a group of data science students, we demonstrate that when training two state-of-the-art abstract image classifiers on Plotly.plus, systems' performance improves more than twice as much as when the original dataset is used, showing that Plotly.plus facilitates the discovery of significant perceptual patterns.