Conversational interfaces are increasingly used for data analysis, enabling data workers to express complex analytical intents in natural language. Yet, these interactions unfold as long, linear transcripts that are misaligned with the iterative, nonlinear nature of real-world analyses. Revisiting and summarizing conversations for different contexts is therefore challenging. This paper investigates how data workers navigate, make sense of, and communicate prior analytical conversations. To study behaviors beyond those supported by standard interfaces (i.e., scrolling and keyword search), we develop a design probe that supplements analytical conversations with structured elements and affordances (e.g., filtering, multi-level navigation and detail-on-demand). In a user study (n = 10), participants used the probe to navigate and communicate past analyses, fulfilling information needs (recall, reorient, prioritize) through navigation strategies (visual recall, sequential and abstractive) and summarization practices (adding process details and context). Based on these findings, we discuss design implications to support re-visitation and communication of analytical conversations.

Language models (LMs) are increasingly being deployed to perform autonomous data analyses. However, their data awareness—the ability to recognize, reason over, and appropriately handle data artifacts such as missing values, outliers, and logical inconsistencies—remains underexplored. These artifacts are especially common in real-world tabular data and, if mishandled, can significantly compromise the validity of analytical conclusions. To address this gap, we present RADAR, a benchmark for systematically evaluating data-aware reasoning on tabular data. We develop a framework to simulate data artifacts via programmatic perturbations to enable targeted evaluation of model behavior. RADAR comprises 2,980 table-query pairs, grounded in real-world data spanning 9 domains and 5 data artifact types. In addition to evaluating artifact handling, RADAR systematically varies table size to study how reasoning performance holds when increasing table size. Our evaluation reveals that, despite decent performance on tables without data artifacts, frontier models degrade significantly when data artifacts are introduced, exposing critical gaps in their capacity for robust, data-aware analysis. Designed to be flexible and extensible, RADAR supports diverse perturbation types and controllable table sizes, offering a valuable resource for advancing tabular reasoning.

Data analysis is challenging as analysts must navigate nuanced decisions that may yield divergent conclusions. AI assistants have the potential to support analysts in planning their analyses, enabling more robust decision making. Though AI-based assistants that target code execution (e.g., Github Copilot) have received significant attention, limited research addresses assistance for both analysis execution and planning. In this work, we characterize helpful planning suggestions and their impacts on analysts’ workflows. We first review the analysis planning literature and crowd-sourced analysis studies to categorize suggestion content. We then conduct a Wizard-of-Oz study (n=13) to observe analysts’ preferences and reactions to planning assistance in a realistic scenario. Our findings highlight subtleties in contextual factors that impact suggestion helpfulness, emphasizing design implications for supporting different abstractions of assistance, forms of initiative, increased engagement, and alignment of goals between analysts and assistants.

Data analysis is challenging as it requires synthesizing domain knowledge, statistical expertise, and programming skills. Assistants powered by large language models (LLMs), such as ChatGPT, can assist analysts by translating natural language instructions into code. However, AI-assistant responses and analysis code can be misaligned with the analyst’s intent or be seemingly correct but lead to incorrect conclusions. Therefore, validating AI assistance is crucial and challenging. Here, we explore how analysts understand and verify the correctness of AI-generated analyses. To observe analysts in diverse verification approaches, we develop a design probe equipped with natural language explanations, code, visualizations, and interactive data tables with common data operations. Through a qualitative user study (n=22) using this probe, we uncover common behaviors within verification workflows and how analysts’ programming, analysis, and tool backgrounds reflect these behaviors. Additionally, we provide recommendations for analysts and highlight opportunities for designers to improve future AI-assistant experiences.

Multiverse analysis—a paradigm for statistical analysis that considers all combinations of reasonable analysis choices in parallel—promises to improve transparency and reproducibility. Although recent tools help analysts specify multiverse analyses, they remain difficult to use in practice. In this work, we identify debugging as a key barrier due to the latency from running analyses to detecting bugs and the scale of metadata processing needed to diagnose a bug. To address these challenges, we prototype a command-line interface tool, Multiverse Debugger, which helps diagnose bugs in the multiverse and propagate fixes. In a qualitative lab study (n=13), we use Multiverse Debugger as a probe to develop a model of debugging workflows and identify specific challenges, including difficulty in understanding the multiverse’s composition. We conclude with design implications for future multiverse analysis authoring systems.

Graph similarity computation is one of the core operations in many graph-based applications, such as graph similarity search, graph database analysis, graph clustering, etc. Since computing the exact distance/similarity between two graphs is typically NP-hard, a series of approximate methods have been proposed with a trade-off between accuracy and speed. Recently, several data-driven approaches based on neural networks have been proposed, most of which model the graph-graph similarity as the inner product of their graph-level representations, with different techniques proposed for generating one embedding per graph. However, using one fixed-dimensional embedding per graph may fail to fully capture graphs in varying sizes and link structures—a limitation that is especially problematic for the task of graph similarity computation, where the goal is to find the fine-grained difference between two graphs. In this paper, we address the problem of graph similarity computation from another perspective, by directly matching two sets of node embeddings without the need to use fixed-dimensional vectors to represent whole graphs for their similarity computation. The model, Graph-Sim, achieves the state-of-the-art performance on four real-world graph datasets under six out of eight settings (here we count a specific dataset and metric combination as one setting), compared to existing popular methods for approximate Graph Edit Distance (GED) and Maximum Common Subgraph (MCS) computation.

We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity. Our approach, UGraphEmb, is a general framework that provides a novel means to performing graph-level embedding in a completely unsupervised and inductive manner. The learned neural network can be considered as a function that receives any graph as input, either seen or unseen in the training set, and transforms it into an embedding. A novel graph-level embedding generation mechanism called Multi-Scale Node Attention (MSNA), is proposed. Experiments on five real graph datasets show that UGraphEmb achieves competitive accuracy in the tasks of graph classification, similarity ranking, and graph visualization.