V-RECS: a NL2Vis Recommender for Chart Generation with Explanations, Captioning, and Suggestions

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.