Steven M. Drucker

Jeevana Priya Inala, Chenglong Wang, Steven Drucker et al. · microsoft-research

This paper explores the potential of AI-powered tools to reshape data analysis, focusing on design considerations and challenges. We explore how the emergence of large language and multimodal models offers new opportunities to enhance various stages of data analysis workflow by translating high-level user intentions into executable code, charts, and insights. We then examine human-centered design principles that facilitate intuitive interactions, build user trust, and streamline the AI-assisted analysis workflow across multiple apps. Finally, we discuss the research challenges that impede the development of these AI-based systems such as enhancing model capabilities, evaluating and benchmarking, and understanding end-user needs.

Sneha Gathani, Sirui Zeng, Diya Patel et al. · mit

What-if analysis (WIA) is an iterative, multi-step process where users explore and compare hypothetical scenarios by adjusting parameters, applying constraints, and scoping data through interactive interfaces. Current tools fall short of supporting effective interactive WIA: spreadsheet and BI tools require time-consuming and laborious setup, while LLM-based chatbot interfaces are semantically fragile, frequently misinterpret intent, and produce inconsistent results as conversations progress. To address these limitations, we present a two-stage workflow that translates natural language (NL) WIA questions into interactive visual interfaces via an intermediate representation, powered by the Praxa Specification Language (PSL): first, LLMs generate PSL specifications from NL questions capturing analytical intent and logic, enabling validation and repair of erroneous specifications; and second, the specifications are compiled into interactive visual interfaces with parameter controls and linked visualizations. We benchmark this workflow with 405 WIA questions spanning 11 WIA types, 5 datasets, and 3 state-of-the-art LLMs. The results show that across models, half of specifications (52.42%) are generated correctly without intervention. We perform an analysis of the failure cases and derive an error taxonomy spanning non-functional errors (specifications fail to compile) and functional errors (specifications compile but misrepresent intent). Based on the taxonomy, we apply targeted repairs on the failure cases using few-shot prompts and improve the success rate to 80.42%. Finally, we show how undetected functional errors propagate through compilation into plausible but misleading interfaces, demonstrating that the intermediate specification is critical for reliably bridging NL and interactive WIA interface in LLM-powered WIA systems.

Chenglong Wang, Bongshin Lee, Steven Drucker et al.

Data analysts often need to iterate between data transformations and chart designs to create rich visualizations for exploratory data analysis. Although many AI-powered systems have been introduced to reduce the effort of visualization authoring, existing systems are not well suited for iterative authoring. They typically require analysts to provide, in a single turn, a text-only prompt that fully describe a complex visualization. We introduce Data Formulator 2 (DF2 for short), an AI-powered visualization system designed to overcome this limitation. DF2 blends graphical user interfaces and natural language inputs to enable users to convey their intent more effectively, while delegating data transformation to AI. Furthermore, to support efficient iteration, DF2 lets users navigate their iteration history and reuse previous designs, eliminating the need to start from scratch each time. A user study with eight participants demonstrated that DF2 allowed participants to develop their own iteration styles to complete challenging data exploration sessions.

Luke S. Snyder, Chenglong Wang, Steven M. Drucker

Despite the ubiquity of visualization examples published on the web, retargeting existing custom chart implementations to new datasets remains difficult, time-intensive, and tedious. The adaptation process assumes author familiarity with both the implementation of the example as well as how the new dataset might need to be transformed to fit into the example code. With recent advances in Large Language Models (LLMs), automatic adaptation of code can be achieved from high-level user prompts, reducing the barrier for visualization retargeting. To better understand how LLMs can assist retargeting and its potential limitations, we characterize and evaluate the performance of LLM assistance across multiple datasets and charts of varying complexity, categorizing failures according to type and severity. In our evaluation, we compare two approaches: (1) directly instructing the LLM model to fully generate and adapt code by treating code as text inputs and (2) a more constrained program synthesis pipeline where the LLM guides the code construction process by providing structural information (e.g., visual encodings) based on properties of the example code and data. We find that both approaches struggle when new data has not been appropriately transformed, and discuss important design recommendations for future retargeting systems.

Benjamin Lee, Dave Brown, Bongshin Lee et al.

A fundamental part of data visualization is transforming data to map abstract information onto visual attributes. While this abstraction is a powerful basis for data visualization, the connection between the representation and the original underlying data (i.e., what the quantities and measurements actually correspond with in reality) can be lost. On the other hand, virtual reality (VR) is being increasingly used to represent real and abstract models as natural experiences to users. In this work, we explore the potential of using VR to help restore the basic understanding of units and measures that are often abstracted away in data visualization in an approach we call data visceralization. By building VR prototypes as design probes, we identify key themes and factors for data visceralization. We do this first through a critical reflection by the authors, then by involving external participants. We find that data visceralization is an engaging way of understanding the qualitative aspects of physical measures and their real-life form, which complements analytical and quantitative understanding commonly gained from data visualization. However, data visceralization is most effective when there is a one-to-one mapping between data and representation, with transformations such as scaling affecting this understanding. We conclude with a discussion of future directions for data visceralization.

Arjun Srinivasan, Bongshin Lee, Nathalie Henry Riche et al.

While tablet devices are a promising platform for data visualization, supporting consistent interactions across different types of visualizations on tablets remains an open challenge. In this paper, we present multimodal interactions that function consistently across different visualizations, supporting common operations during visual data analysis. By considering standard interface elements (e.g., axes, marks) and grounding our design in a set of core concepts including operations, parameters, targets, and instruments, we systematically develop interactions applicable to different visualization types. To exemplify how the proposed interactions collectively facilitate data exploration, we employ them in a tablet-based system, InChorus that supports pen, touch, and speech input. Based on a study with 12 participants performing replication and fact-checking tasks with InChorus, we discuss how participants adapted to using multimodal input and highlight considerations for future multimodal visualization systems.