Related papers: Data Formulator 2: Iterative Creation of Data Visu…
Charts and graphs help people analyze data, but can they also be useful to AI systems? To investigate this question, we perform a series of experiments with two commercial vision-language models: GPT 4.1 and Claude 3.5. Across three…
Traditional Data+AI systems utilize data-driven techniques to optimize performance, but they rely heavily on human experts to orchestrate system pipelines, enabling them to adapt to changes in data, queries, tasks, and environments. For…
Data-to-text (D2T) generation aims to transform structured data into natural language text. Data-to-text pre-training has proved to be powerful in enhancing D2T generation and yields impressive performances. However, previous pre-training…
Interactive visualizations are powerful tools for Exploratory Data Analysis (EDA), but how do they affect the observations analysts make about their data? We conducted a qualitative experiment with 13 professional data scientists analyzing…
Data Visualization has become an important aspect of big data analytics and has grown in sophistication and variety. We specifically identify the need for an analytical framework for data visualization with textual information. Data…
Constructive approaches to visualization authoring have been shown to offer advantages such as providing options for flexible outputs, scaffolding and ideation of new data mappings, personalized exploration of data, as well as supporting…
Traditional visualisation designers often start with sketches before implementation. With generative AI, these sketches can be turned into AI-generated visualisations using specific prompts. However, guiding AI to create compelling visuals…
Data visualization is essential for interpreting complex datasets, yet traditional tools often require technical expertise, limiting accessibility. VizGen is an AI-assisted graph generation system that empowers users to create meaningful…
In healthcare, AI techniques are widely used for tasks like risk assessment and anomaly detection. Despite AI's potential as a valuable assistant, its role in complex medical data analysis often oversimplifies human-AI collaboration…
In the digital landscape, the ubiquity of data visualizations in media underscores the necessity for accessibility to ensure inclusivity for all users, including those with visual impairments. Current visual content often fails to cater to…
Recent progress in scientific visualization has expanded the scope of visualization from being merely a way of presentation to an analysis and discovery tool. A given visualization result is usually generated by applying a series of…
Tabular question answering (TQA) presents a challenging setting for neural systems by requiring joint reasoning of natural language with large amounts of semi-structured data. Unlike humans who use programmatic tools like filters to…
Computational notebooks, while essential for data science, are limited by their one-dimensional interface, which poorly aligns with non-linear developer workflows and complicates collaboration and human-AI interaction. In this work, we…
Large language models (LLMs) can reshape information processing by handling data analysis, visualization, and interpretation in an interactive, context-aware dialogue with users, including voice interaction, while maintaining high…
This paper revisits the role of quantitative and qualitative methods in visualization research in the context of advancements in artificial intelligence (AI). The focus is on how we can bridge between the different methods in an integrated…
Image classification models often learn to predict a class based on irrelevant co-occurrences between input features and an output class in training data. We call the unwanted correlations "data biases," and the visual features causing data…
The new age of digital growth has marked all fields. This technological evolution has impacted data flows which have witnessed a rapid expansion over the last decade that makes the data traditional processing unable to catch up with the…
This paper introduces semi-automatic data tours to aid the exploration of complex networks. Exploring networks requires significant effort and expertise and can be time-consuming and challenging. Distinct from guidance and recommender…
We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize…
Table Question Answering (TableQA) enables natural language interaction with structured tabular data. However, existing large language model (LLM) approaches face critical limitations: context length constraints that restrict data handling…