Modern talking-visuallybookmark_border

Causal networks are widely used in many fields to model the complex relationships between variables. A recent approach has sought to construct causal networks by leveraging the wisdom of crowds through the collective participation of humans. While this can yield detailed causal networks that model the underlying phenomena quite well, it requires a large number of individuals with domain understanding. We adopt a different approach: leveraging the causal knowledge that large language models, such as OpenAI's GPT-4, have learned by ingesting massive amounts of literature. Within a dedicated visual analytics interface, called CausalChat, users explore single variables or variable pairs recursively to identify causal relations, latent variables, confounders, and mediators, constructing detailed causal networks through conversation. Each probing interaction is translated into a tailored GPT-4 prompt and the response is conveyed through visual representations which are linked to the generated text for explanations. We demonstrate the functionality of CausalChat across diverse data contexts and conduct user studies involving both domain experts and laypersons.

Users typically interact with and evaluate language models via single outputs, where each output is just one sample from a broad distribution of possible completions. This interaction hides distributional structure such as modes, uncommon edge cases, and sensitivity to small prompt changes, leading users to over-generalize from anecdotes when iterating on prompts for open-ended tasks. We conduct a formative study with researchers who use LMs (n = 13) examining when stochasticity matters in practice, how they reason about distributions over language, and where current workflows break down. Informed by this study, we introduce GROVE, an interactive visualization that represents multiple LM generations as overlapping paths through a text graph, revealing shared structure, branching points, and clusters while preserving access to raw outputs. We evaluate across three crowdsourced user studies (N = 47, 44, and 40 participants) targeting complementary distributional tasks. Our results support a hybrid workflow: graph summaries improve structural judgments (e.g., assessing LM output diversity), while direct output inspection remains more effective for detail-oriented tasks.

Chart descriptions are essential for accessibility, cross-modal retrieval, and assisting readers in extracting insights from complex visualizations. As multimodal large language models (MLLMs) are increasingly adopted for automated chart description generation, a critical question arises: how faithfully and insightfully do these models actually describe charts? Current benchmarks fall short on two fronts: existing datasets consist of simple, homogeneous charts paired with shallow, fact-enumerating descriptions; and prevailing metrics fail to capture the multi-faceted nature of description quality. To address these gaps, we present the Chart Faithfulness and Insightfulness Benchmark (ChartFI-Bench). We first summarize four dimensions that characterize high-quality chart descriptions: factual accuracy, salient feature emphasis, domain-informed guidance, and chart–text complementarity. Guided by these dimensions, we construct a high-quality benchmark comprising 896 chart--description pairs, which feature visually complex charts and semantically rich descriptions. Furthermore, we design four aligned evaluation metrics---Faithfulness, Coverage, Informativeness, and Acuity---to systematically assess the quality of descriptions across these dimensions. Experiments conducted on mainstream MLLMs demonstrate the effectiveness of the proposed framework and reveal common weaknesses among existing models.

Designing transfer functions (TFs) for direct volume rendering is a fundamental yet labor-intensive task, as users need to carefully explore the relationship between voxel attributes and visual outcomes to reveal structures of interest. Despite advances in learning-based approaches, many existing methods depend on repeated user input. Furthermore, many methods relying on conventional data value-based TFs, which use voxel intensity or gradient information, often struggle to separate voxels into meaningful semantic groups. To address these problems, we present a framework that enables automatic TF design via multimodal large language model (MLLM)-assisted 2D semantic decomposition, requiring only minimal user input, namely the volume name and a projection axis. Starting from a single maximum intensity projection of the volume, our method transforms it into a semantic segmentation mask using an MLLM, which is then lifted into 3D as a sparse set of reliable voxel cues. To convert these sparse cues into a complete semantic representation, we introduce a voxel classification network trained with a confidence-aware propagation loss, resulting in dense voxel-level semantic assignments that are readily translated into TFs. Despite relying solely on single-image segmentation, our method achieves precise part-level separation. Evaluation on a range of volume datasets shows that ours produces better semantic renderings while significantly reducing the effort and time required for TF design compared to state-of-the-art techniques.

In this paper, we test whether Multimodal Large Language Models (MLLMs) can match human-subject performance in tasks involving the perception of properties in network layouts. Specifically, we replicate a human-subject experiment about perceiving quality (namely stress) in network layouts using GPT-4o, Gemini-2.5 and Qwen2.5. Our experiments show that giving MLLMs the same study information as trained human participants yields performance comparable to that of human experts and exceeds that of untrained non-experts. Additionally, we show that prompt engineering that deviates from the human-subject experiment can lead to better-than-human performance in some settings. Interestingly, like human subjects, the MLLMs seem to rely on visual proxies rather than computing the actual value of stress, indicating some sense or facsimile of perception. Explanations from the models are similar to those used by the human participants (e.g., an even distribution of nodes and uniform edge lengths).

Visual data analysis involves both open-ended exploration and targeted question answering. Visualization authoring tools support this process by enabling users to create visualizations for these tasks. With the rise of large language models (LLMs), substantial effort has been devoted to developing visualization authoring tools that use natural language instructions. However, existing systems are typically based on a linear chat interface, which is not well suited to exploratory visual analysis workflows. In this paper, we introduce VisCanvas, a node-based interface for exploratory visualization authoring with LLMs. VisCanvas allows users to create, revise, branch, and merge visualizations in a non-linear way, enabling more efficient exploration of multiple analytical directions. We conducted a user study with 20 participants to evaluate the effectiveness of VisCanvas compared to a baseline chat-based interface. The results show that VisCanvas facilitates more diverse data interaction while maintaining performance levels (i.e., cognitive load and usability) that are indistinguishable from current prevailing methods. We then distill design principles for future AI-assisted visualization authoring environments. All supplemental materials required to reproduce the study are available at https://osf.io/gsxhn.

We present Flint, an intermediate language that enables authors to create high-quality visualizations from concise, semantics-driven specifications without explicitly configuring low-level parameters such as scales, axes, and formatting. Unlike prior systems that infer default configurations from surface-level data representations, often producing brittle choices, Flint introduces a hierarchical data semantic model that allows users to specify the meanings of data fields structurally and helps the compiler derive appropriate visualization configurations. From a concise specification, the system generates and optimizes library-agnostic visualization configurations and translates them into complete, executable specifications for multiple target grammars, including Vega-Lite, Apache ECharts, and Chart.js. We demonstrate that Flint simplifies the authoring process without compromising on visual quality, and it is an effective intermediate language for both humans and AI agents to create visualizations.